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

    Neuronpedia

    INDEX
    Explanations

    terms related to disclosure and information reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicit
    -0.15
    arry
    -0.14
    sko
    -0.14
    holds
    -0.13
    rollo
    -0.13
    lar
    -0.13
    /if
    -0.13
    ATAB
    -0.13
    elman
    -0.13
    elu
    -0.13
    POSITIVE LOGITS
    ramer
    0.15
    MBER
    0.14
    ibly
    0.14
    nature
    0.14
    idot
    0.14
    вÑĥ
    0.14
    CursorPosition
    0.14
    edad
    0.14
    acen
    0.14
    oÄį
    0.14
    Act Density 0.010%

    No Known Activations