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

    Neuronpedia

    INDEX
    Explanations

    mentions of form structures and types in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idges
    -0.17
     Ansi
    -0.14
    jaw
    -0.14
    à¹ĭ
    -0.14
    idas
    -0.14
    _SAMPL
    -0.14
    .setTo
    -0.14
    Æ¡
    -0.14
    aight
    -0.14
    quo
    -0.14
    POSITIVE LOGITS
     Group
    0.21
    -group
    0.21
    Group
    0.20
     group
    0.19
     Mist
    0.19
     GROUP
    0.18
     grup
    0.18
    -horizontal
    0.17
    _group
    0.17
     Groups
    0.17
    Act Density 0.010%

    No Known Activations