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

    Neuronpedia

    INDEX
    Explanations

    phrases related to occurrences or events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    step
    -1.03
    ilts
    -1.02
    edged
    -0.98
    acked
    -0.92
    shaw
    -0.91
    hub
    -0.89
    tip
    -0.87
    oos
    -0.87
    edo
    -0.87
    pa
    -0.86
    POSITIVE LOGITS
    uate
    1.23
    rences
    1.18
    uated
    1.03
     anew
    1.00
    uating
    0.97
    uates
    0.95
     upon
    0.88
    uation
    0.86
    uations
    0.82
     occurring
    0.80
    Act Density 0.769%

    No Known Activations