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

    Neuronpedia

    INDEX
    Explanations

    text with specific formatting elements or symbols, indicating a focus on technical and structured information typical in scientific or academic documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.71
    */;
    -0.67
     Efq
    -0.64
    ODY
    -0.62
    igua
    -0.60
    TagMode
    -0.60
    ecute
    -0.58
     Chrift
    -0.58
    tahui
    -0.57
    \}\\
    -0.57
    POSITIVE LOGITS
    detectChanges
    0.67
    InjectAttribute
    0.64
    AndEndTag
    0.59
    WireFormat
    0.54
    <bos>
    0.54
     it
    0.52
     there
    0.50
     natten
    0.48
     thither
    0.48
    interopRequire
    0.48
    Act Density 0.535%

    No Known Activations