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

    Neuronpedia

    INDEX
    Explanations

    percentages or related numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.78
    zek
    -0.76
    ITED
    -0.70
    imir
    -0.69
     Tycoon
    -0.68
    åİ
    -0.67
    pecially
    -0.67
    ãĥ¤
    -0.65
    adr
    -0.64
    ãĥīãĥ©
    -0.63
    POSITIVE LOGITS
     percent
    0.89
    percent
    0.86
     Percent
    0.76
    rowth
    0.72
    lein
    0.71
    imeter
    0.69
    enhagen
    0.67
    Percent
    0.66
    cake
    0.66
    eele
    0.65
    Act Density 0.034%

    No Known Activations