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

    Neuronpedia

    INDEX
    Explanations

    elements related to alignment in design or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.85
    rawDesc
    -0.84
     ModelExpression
    -0.84
     يتيمه
    -0.83
    verifyException
    -0.80
    tagHelperRunner
    -0.79
    MessageState
    -0.79
    StructEnd
    -0.79
    حياتها
    -0.77
     Réponses
    -0.74
    POSITIVE LOGITS
     ALIGN
    0.65
    ignment
    0.64
    ments
    0.60
     valign
    0.58
     pins
    0.55
     alig
    0.54
    TextAlignment
    0.53
    pins
    0.52
     alignments
    0.52
    visuel
    0.51
    Act Density 0.165%

    No Known Activations