© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    instances of speaking or talking

    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
    �
    -0.72
    luaj
    -0.68
     2014
    -0.68
    bows
    -0.67
    udeau
    -0.65
     2015
    -0.64
     hail
    -0.63
    sov
    -0.60
    ousy
    -0.60
    龍�
    -0.58
    POSITIVE LOGITS
    room
    0.81
    tered
    0.68
    aroo
    0.68
    989
    0.65
    enough
    0.65
    887
    0.65
    ensable
    0.64
    wing
    0.64
    illion
    0.63
    eeper
    0.63
    Activations Density 0.054%

    No Known Activations