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

    Neuronpedia

    INDEX
    Explanations

    statements that express beliefs, assertions, or claims made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.89
    GraphicsUnit
    -0.80
     Мексичка
    -0.77
    VersionUID
    -0.73
    InputBorder
    -0.73
    AndEndTag
    -0.70
    AutoScaleMode
    -0.69
    AccessorTable
    -0.68
     propOrder
    -0.68
    -0.66
    POSITIVE LOGITS
     could
    0.49
     which
    0.48
    tamanya
    0.48
     attivo
    0.47
     requiring
    0.46
     fits
    0.46
     ativo
    0.46
     pinggang
    0.45
     requires
    0.45
    anwalt
    0.45
    Act Density 0.215%

    No Known Activations