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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the name "Brooks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ministic
    -0.79
    awei
    -0.78
    ality
    -0.72
    izen
    -0.72
    ugal
    -0.68
    TY
    -0.68
    izoph
    -0.67
    inel
    -0.66
    igators
    -0.66
     elig
    -0.65
    POSITIVE LOGITS
     Brothers
    0.93
    oks
    0.90
    boro
    0.80
    ãģĨ
    0.80
    combe
    0.76
    dale
    0.76
     Reed
    0.74
     Fargo
    0.73
    leys
    0.71
    mire
    0.71
    Act Density 0.064%

    No Known Activations