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

    Neuronpedia

    INDEX
    Explanations

    indentations and formatting typical of code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellas
    -0.17
    atk
    -0.16
    emed
    -0.14
    arkan
    -0.14
     nick
    -0.14
    irk
    -0.14
    riday
    -0.13
     exped
    -0.13
    nik
    -0.13
    ampp
    -0.13
    POSITIVE LOGITS
    _SDK
    0.15
    unbind
    0.15
    hu
    0.14
    лам
    0.14
     Ville
    0.14
     Roose
    0.13
    akash
    0.13
    .interpolate
    0.13
    OKIE
    0.13
    wig
    0.13
    Act Density 0.003%

    No Known Activations