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

    Neuronpedia

    INDEX
    Explanations

    words related to events happening or taking place

    oai_token-act-pair · gpt-3.5-turbo

    the verb "occur" and its variations related to events or phenomena happening at specific times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.83
    step
    -0.75
    edged
    -0.75
    iled
    -0.72
    grown
    -0.70
    shaw
    -0.69
    acked
    -0.68
    edge
    -0.66
    tip
    -0.64
    axter
    -0.64
    POSITIVE LOGITS
    uate
    1.23
    rences
    1.02
    uated
    0.97
    uates
    0.95
    uating
    0.91
    uation
    0.85
    uations
    0.79
     anew
    0.77
     [&
    0.71
     occurring
    0.69
    Act Density 0.036%

    No Known Activations