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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases

    oai_token-act-pair · gpt-3.5-turbo

    negative symbols or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.78
     appropri
    -0.73
     chained
    -0.65
     incorpor
    -0.62
     pro
    -0.62
    atron
    -0.60
    iciary
    -0.60
     incarnation
    -0.60
     thrust
    -0.59
     decon
    -0.59
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    1.18
    =-=-=-=-
    1.08
    sama
    1.04
    webkit
    0.95
    _-
    0.93
    *=-
    0.85
     Advertisement
    0.84
    sized
    0.82
    based
    0.77
    agers
    0.76
    Act Density 0.033%

    No Known Activations