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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.61
    kefeller
    -0.61
    mentioned
    -0.61
    hetti
    -0.58
    redo
    -0.54
    rums
    -0.52
    eday
    -0.52
    anwhile
    -0.52
    urer
    -0.52
     curric
    -0.51
    POSITIVE LOGITS
     total
    0.77
     Overall
    0.70
    ãĥ¼ãĤ¯
    0.70
     avg
    0.64
    Downloadha
    0.63
    Total
    0.61
    total
    0.61
     overall
    0.61
    pes
    0.60
     Fahrenheit
    0.58
    Act Density 0.401%

    No Known Activations