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

    Neuronpedia

    INDEX
    Explanations

    words related to corporations and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corporate and vertebrate subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.75
    essee
    -0.69
     contestant
    -0.66
     incent
    -0.64
    flix
    -0.64
    isphere
    -0.63
     brace
    -0.63
     challeng
    -0.63
     crack
    -0.61
    papers
    -0.61
    POSITIVE LOGITS
    REDACTED
    0.78
     Liberties
    0.74
     Vers
    0.74
    assis
    0.74
    Saharan
    0.73
    porate
    0.70
    ODUCT
    0.70
    hammad
    0.68
    ather
    0.68
    ctr
    0.67
    Act Density 0.042%

    No Known Activations