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

    Neuronpedia

    INDEX
    Explanations

    syntax structures and specific formatting conventions in code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.73
    UnsafeEnabled
    -0.69
    awtextra
    -0.66
    IndentedString
    -0.66
    ArgsConstructor
    -0.66
     referenties
    -0.64
    TintMode
    -0.62
     AttributeSet
    -0.61
    eradish
    -0.61
    PreferredItem
    -0.59
    POSITIVE LOGITS
    iglesia
    0.52
     그것
    0.50
     disponibilités
    0.49
     TÉCNICA
    0.49
    Grave
    0.49
     TAMBÉM
    0.48
     版本
    0.47
    zeki
    0.46
     TÉCN
    0.46
    máscara
    0.46
    Act Density 0.516%

    No Known Activations