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

    Neuronpedia

    INDEX
    Explanations

    mentions of travelling or exploring different places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.82
    pez
    -0.82
    umbn
    -0.79
    ources
    -0.78
    uffle
    -0.75
    ngth
    -0.74
    cius
    -0.72
    ERE
    -0.71
    rez
    -0.71
    opia
    -0.71
    POSITIVE LOGITS
    hw
    0.73
     Sylv
    0.70
     MSI
    0.69
    lishing
    0.59
     Kn
    0.59
    hammad
    0.59
     capit
    0.59
     Wings
    0.58
     spectators
    0.58
     Tsukuyomi
    0.58
    Act Density 0.000%

    No Known Activations