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

    Neuronpedia

    INDEX
    Explanations

    generic phrases indicating comprehensiveness or entirety

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictionary
    -0.63
    ister
    -0.63
    clair
    -0.60
    wen
    -0.60
    =[
    -0.58
    OTAL
    -0.58
    PLA
    -0.58
    alion
    -0.58
    ror
    -0.57
    ALSE
    -0.57
    POSITIVE LOGITS
     usual
    0.80
     way
    0.79
     sudden
    0.78
     requisite
    0.73
     goddamn
    0.70
     slightest
    0.69
     same
    0.68
    things
    0.68
    important
    0.67
     bells
    0.66
    Act Density 0.052%

    No Known Activations