Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 387
    Prev
    Next
    INDEX
    Explanations

    references to bringing people or groups together

    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
    raid
    -0.66
    ís
    -0.66
    bey
    -0.63
    arse
    -0.63
    strap
    -0.63
    grown
    -0.60
    rongh
    -0.59
    trust
    -0.59
    inates
    -0.59
    usp
    -0.59
    POSITIVE LOGITS
    anwhile
    0.74
     forward
    0.73
    ORPG
    0.64
     Dancing
    0.63
    ═
    0.63
    nels
    0.63
     Metatron
    0.63
     undue
    0.60
     INTO
    0.60
     commentary
    0.59
    Activations Density 0.134%

    No Known Activations