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

    Neuronpedia

    INDEX
    Explanations

    references to classes or categories within a structured format, such as HTML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lers
    -0.17
    ateur
    -0.16
    informatics
    -0.15
    bars
    -0.15
    iedo
    -0.15
     gravid
    -0.15
    obar
    -0.14
    baru
    -0.14
    heel
    -0.14
     bars
    -0.14
    POSITIVE LOGITS
    аниÑĨ
    0.17
    mann
    0.16
    sah
    0.16
    RAINT
    0.14
    wins
    0.14
    ansi
    0.14
    .sam
    0.14
     Sah
    0.14
    IMIZE
    0.14
    agan
    0.14
    Act Density 0.006%

    No Known Activations