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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents, typically indicating names or references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äı
    -0.17
    364
    -0.15
    redo
    -0.14
    aine
    -0.14
    534
    -0.14
    abad
    -0.14
    å´İ
    -0.13
    Ñīик
    -0.13
    ê¶ģ
    -0.13
    /actions
    -0.13
    POSITIVE LOGITS
    Äĥm
    0.17
    acro
    0.17
    adas
    0.15
     Wind
    0.14
    ÑĢиз
    0.14
    ongs
    0.14
    人æīį
    0.14
    ladatel
    0.13
    ivet
    0.13
    _wind
    0.13
    Act Density 0.005%

    No Known Activations