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

    Neuronpedia

    INDEX
    Explanations

    words related to statistics and data

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.78
     bodily
    -0.70
     prosec
    -0.70
     tremend
    -0.69
     mates
    -0.66
    yip
    -0.66
     exha
    -0.66
     disemb
    -0.66
     nodd
    -0.65
     bang
    -0.65
    POSITIVE LOGITS
     Now
    1.91
     Today
    1.87
    Today
    1.64
    Now
    1.60
     Later
    1.45
     Then
    1.44
     Since
    1.40
    now
    1.29
     Afterwards
    1.29
    Fast
    1.29
    Act Density 0.556%

    No Known Activations