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

    Neuronpedia

    INDEX
    Explanations

    references to family interactions and quality time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.47
     rouges
    -0.46
     str
    -0.43
     yder
    -0.43
    Drv
    -0.43
     (
    -0.42
     prét
    -0.42
    เข
    -0.42
     izd
    -0.42
     monté
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.81
    UIControlState
    0.81
     enjoyment
    0.79
     socialization
    0.78
    CppMethod
    0.77
    Relax
    0.74
     socialize
    0.72
     socializing
    0.71
     متعلقه
    0.70
     pleaſure
    0.69
    Act Density 0.190%

    No Known Activations