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

    Neuronpedia

    INDEX
    Explanations

    words related to revisions and corrections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to revision and perfectionism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ago
    -0.80
     Clancy
    -0.70
     Feather
    -0.69
     Liberties
    -0.69
    resp
    -0.68
     Mig
    -0.66
     Proced
    -0.65
    DIV
    -0.65
    ãĥ£
    -0.64
    GH
    -0.64
    POSITIVE LOGITS
    ist
    1.38
    ism
    1.36
    ists
    1.36
    istically
    1.01
    istic
    0.99
    isms
    0.93
    istical
    0.91
    IST
    0.91
    istas
    0.90
    aries
    0.89
    Act Density 0.065%

    No Known Activations