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

    Neuronpedia

    INDEX
    Explanations

    special characters related to text formatting

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in a generic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.89
    ierrez
    -0.82
    ebus
    -0.79
    aminer
    -0.75
    ilater
    -0.69
    illas
    -0.67
     philos
    -0.67
    ription
    -0.66
    gdala
    -0.64
     rake
    -0.64
    POSITIVE LOGITS
    ħ
    1.11
    ¾
    1.02
    Ĥª
    0.96
    °
    0.94
    µ
    0.92
    İ
    0.92
    Ĩ
    0.90
    ¼
    0.90
    ŀ
    0.89
    ķ
    0.88
    Act Density 0.003%

    No Known Activations