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

    Neuronpedia

    INDEX
    Explanations

    references to wild animals or wild-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.87
    IsContent
    -0.85
     незавершена
    -0.83
    iedział
    -0.81
    RectangleBorder
    -0.75
    ztály
    -0.74
    OGND
    -0.74
    adaptiveStyles
    -0.72
    ValueStyle
    -0.72
    estors
    -0.71
    POSITIVE LOGITS
     wild
    1.70
     Wild
    1.67
    Wild
    1.65
    wild
    1.60
     WILD
    1.59
    WILD
    1.43
     Wildcats
    1.25
     wilder
    1.20
     wildfire
    1.15
     Wilder
    1.14
    Act Density 0.089%

    No Known Activations