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

    Neuronpedia

    INDEX
    Explanations

    terms related to program configurations and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .datab
    -0.14
    ugg
    -0.13
    roit
    -0.13
    ãģ¤ãģ¶
    -0.12
    s
    -0.12
    alias
    -0.12
    ниÑĨ
    -0.12
    iard
    -0.12
    elp
    -0.12
    olib
    -0.12
    POSITIVE LOGITS
    istrovstvÃŃ
    0.16
    inspace
    0.15
    edback
    0.14
    processable
    0.14
    rary
    0.13
    Uvs
    0.13
    hend
    0.13
    gett
    0.13
    kün
    0.13
    efore
    0.13
    Act Density 0.857%

    No Known Activations