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

    Neuronpedia

    INDEX
    Explanations

    percentages expressed as numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to percentage changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.67
    pton
    -0.64
    ©¶æ
    -0.64
    \\\\\\\\\\\\\\\\
    -0.60
    gotten
    -0.58
     larg
    -0.57
     prizes
    -0.57
     neighb
    -0.57
    åİ
    -0.57
    ãĥ¤
    -0.57
    POSITIVE LOGITS
    xual
    0.96
    bps
    0.80
    asin
    0.74
    +.
    0.73
    +,
    0.73
     ABV
    0.72
    fal
    0.71
    elsius
    0.71
    rowth
    0.71
    uary
    0.70
    Act Density 0.085%

    No Known Activations