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

    Neuronpedia

    INDEX
    Explanations

    special characters that are part of a specific sequence

    oai_token-act-pair · gpt-3.5-turbo

    non-verbal symbols, or character counts without specific context, to identify structured data or meta-information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.83
     ageing
    -0.72
     hiber
    -0.70
     newcom
    -0.69
     tremend
    -0.65
     eleph
    -0.64
    cffff
    -0.64
     aging
    -0.63
    arten
    -0.62
    doms
    -0.62
    POSITIVE LOGITS
    PHOTOS
    0.88
    Trend
    0.86
    @
    0.80
    BRE
    0.79
    Loading
    0.78
    Fans
    0.78
    Rum
    0.78
    Looks
    0.77
    Original
    0.75
     @
    0.75
    Act Density 0.170%

    No Known Activations