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

    Neuronpedia

    INDEX
    Explanations

    mentions of professional associations or organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    steen
    -0.78
    tty
    -0.78
    ashtra
    -0.72
    matter
    -0.71
    gow
    -0.69
    lain
    -0.65
     guise
    -0.63
    ebook
    -0.63
    arium
    -0.62
    trap
    -0.62
    POSITIVE LOGITS
     Chiefs
    0.95
     Independent
    0.82
     Arbit
    0.76
     Non
    0.74
     Pacific
    0.72
     Professional
    0.70
     Coun
    0.70
     Standards
    0.69
     Voters
    0.68
     Persons
    0.68
    Act Density 0.085%

    No Known Activations