© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2587
    Prev
    Next
    INDEX
    Explanations

    concepts related to calming or easing tension in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.66
     tempor
    -0.62
    UES
    -0.61
    isode
    -0.59
    soDeliveryDate
    -0.59
    ティ
    -0.58
     brav
    -0.57
    iami
    -0.55
     sidx
    -0.54
    joice
    -0.54
    POSITIVE LOGITS
     ante
    0.75
    oss
    0.74
    roo
    0.72
    english
    0.70
    otom
    0.66
    rote
    0.63
    arb
    0.63
    owler
    0.62
    rez
    0.61
    yang
    0.61
    Activations Density 0.115%

    No Known Activations