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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe humorous or amusing circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.49
     carbón
    -0.49
    Tembelea
    -0.45
     Horowitz
    -0.44
    ◀
    -0.44
     дописавши
    -0.43
    contentLoaded
    -0.43
     getRule
    -0.42
     constitucional
    -0.42
    binder
    -0.41
    POSITIVE LOGITS
     swimming
    2.05
     swim
    2.03
     swims
    1.94
     swam
    1.85
     swimmers
    1.85
     Swim
    1.83
     Swimming
    1.81
    swim
    1.79
     swimmer
    1.76
    Swim
    1.75
    Act Density 0.386%

    No Known Activations