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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical identifiers or categories and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zim
    -0.17
     semiclass
    -0.17
     Bias
    -0.16
    izo
    -0.16
    ome
    -0.15
    tero
    -0.14
     \/
    -0.14
    év
    -0.14
    .toolbox
    -0.14
    ãĤ¡
    -0.13
    POSITIVE LOGITS
    óng
    0.16
     Produ
    0.15
     Inc
    0.15
    dÄĽ
    0.15
    gba
    0.15
     ============================================================================↵
    0.15
    ummer
    0.15
     Od
    0.15
    etag
    0.14
     syn
    0.14
    Act Density 0.001%

    No Known Activations