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

    Neuronpedia

    INDEX
    Explanations

    present tense verbs followed by 'is'

    oai_token-act-pair · gpt-3.5-turbo

    statements or predicates that articulate an assertion or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.83
    rive
    -0.63
    croft
    -0.63
    ventures
    -0.62
    olls
    -0.62
    waukee
    -0.60
    cookie
    -0.60
    elve
    -0.59
    styles
    -0.58
    chev
    -0.58
    POSITIVE LOGITS
     especially
    0.99
     contrasted
    0.95
     partly
    0.95
     why
    0.93
     understandable
    0.93
     evidenced
    0.91
     particularly
    0.89
     reflected
    0.88
     compounded
    0.88
     exacerbated
    0.88
    Act Density 0.142%

    No Known Activations