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

    Neuronpedia

    INDEX
    Explanations

    elements related to evaluation or assessment of behavior and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.62
    ✭✭
    -0.61
    XmlType
    -0.60
     الدولى
    -0.60
    tagHelperRunner
    -0.59
    LookAnd
    -0.59
    ::$_
    -0.58
    yship
    -0.58
     abbraccio
    -0.58
    tonsoft
    -0.57
    POSITIVE LOGITS
     personnaliser
    0.52
    extAlignment
    0.51
     special
    0.50
    invokeLater
    0.49
     temática
    0.48
     contexte
    0.47
     Spes
    0.47
    Tarih
    0.46
    cond
    0.45
     themed
    0.45
    Act Density 0.453%

    No Known Activations