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

    Neuronpedia

    INDEX
    Explanations

    events or sequences of events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant occurrences or happenings in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unicip
    -0.77
    ickets
    -0.72
    oug
    -0.69
    ench
    -0.68
    olls
    -0.67
    ateurs
    -0.67
     Excellence
    -0.66
     pigeon
    -0.66
    ply
    -0.65
    icrobial
    -0.65
    POSITIVE LOGITS
     transpired
    1.30
     unfolded
    1.25
     unfolding
    1.22
     unfold
    1.19
     happened
    0.98
    uate
    0.95
    uating
    0.91
     events
    0.88
     occurring
    0.85
    uates
    0.85
    Act Density 0.056%

    No Known Activations