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

    Neuronpedia

    INDEX
    Explanations

    names of people, particularly Trevor, Shaun, Geoff, and Trent

    oai_token-act-pair · gpt-3.5-turbo

    specific names, particularly of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.87
    tre
    -0.86
    gran
    -0.80
    keye
    -0.80
    asin
    -0.80
    ascript
    -0.76
    mates
    -0.76
    friend
    -0.75
    hammad
    -0.75
    Magikarp
    -0.75
    POSITIVE LOGITS
     Rez
    0.93
     Trevor
    0.89
     Watts
    0.87
     Amos
    0.83
     Higgins
    0.80
     Strauss
    0.77
     Siem
    0.76
     Rodgers
    0.76
     Carey
    0.76
     Duffy
    0.75
    Act Density 0.046%

    No Known Activations