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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "working" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    antha
    -0.76
    ylon
    -0.71
     Augustus
    -0.66
    emonic
    -0.66
     Bubble
    -0.66
    anamo
    -0.64
     constitu
    -0.63
    xual
    -0.62
    angular
    -0.61
    iren
    -0.60
    POSITIVE LOGITS
     tirelessly
    1.13
    bench
    1.08
    hops
    1.03
     diligently
    1.03
     collabor
    0.99
     ethic
    0.98
     overtime
    0.97
    heet
    0.94
    paces
    0.86
    station
    0.85
    Act Density 0.333%

    No Known Activations