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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the year 2018

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.74
    irds
    -0.68
    iazep
    -0.68
     entitle
    -0.65
    edIn
    -0.65
    olicy
    -0.63
     wre
    -0.62
     everyday
    -0.62
     expire
    -0.62
     lull
    -0.61
    POSITIVE LOGITS
    emphasis
    1.19
    see
    1.15
    sic
    1.09
    ...)
    1.09
    via
    1.06
    also
    1.05
    formerly
    1.05
    including
    1.05
    which
    1.01
    /)
    1.00
    Act Density 0.143%

    No Known Activations