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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    structurally complex phrases or contextual mentions of entities like locations and historical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etime
    -0.71
    ragon
    -0.68
    TeX
    -0.62
    Otherwise
    -0.61
    ometry
    -0.60
    é¾į
    -0.60
     estab
    -0.59
    eway
    -0.59
    cko
    -0.58
    Hide
    -0.58
    POSITIVE LOGITS
     these
    0.77
     this
    0.73
    these
    0.72
    this
    0.64
     it
    0.61
     respectively
    0.60
     Garland
    0.59
    angular
    0.58
     Vaughan
    0.57
     McDonnell
    0.56
    Act Density 0.455%

    No Known Activations