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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "jack."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "jack"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frag
    -0.77
     Towns
    -0.71
     Viet
    -0.70
     Corpus
    -0.70
     CONT
    -0.65
     Parent
    -0.65
    uve
    -0.64
     Diet
    -0.64
     Schwar
    -0.64
    phrine
    -0.64
    POSITIVE LOGITS
    ety
    1.06
    nell
    1.04
    intosh
    1.04
    hammer
    1.00
    awaru
    0.99
    knife
    0.99
    nels
    0.95
    ument
    0.94
    assian
    0.93
    pots
    0.93
    Act Density 0.024%

    No Known Activations