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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of the people or entities responsible for a particular project, action, or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to people or entities responsible for specific actions or creations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cki
    -0.82
    ism
    -0.76
    theless
    -0.67
    ck
    -0.67
    ander
    -0.67
    WI
    -0.66
    istic
    -0.65
    isms
    -0.64
    ize
    -0.63
    ude
    -0.63
    POSITIVE LOGITS
     bars
    0.81
     why
    0.70
     closed
    0.67
     Closed
    0.65
     Bars
    0.64
     unlocking
    0.64
     such
    0.63
     the
    0.62
    rils
    0.62
     these
    0.61
    Act Density 0.039%

    No Known Activations