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

    Neuronpedia

    INDEX
    Explanations

    concepts related to absurdity

    oai_token-act-pair · gpt-3.5-turbo

    references to absurdity or outlandish claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enfranch
    -0.90
    ribution
    -0.79
    rounder
    -0.78
    Reviewed
    -0.77
    yer
    -0.77
    builders
    -0.76
    oother
    -0.75
    rien
    -0.74
    icket
    -0.72
    gio
    -0.70
    POSITIVE LOGITS
    ly
    1.01
     amounts
    0.97
     proportions
    0.93
    LY
    0.89
    ishly
    0.85
    ities
    0.84
     asylum
    0.83
     lengths
    0.83
     amount
    0.82
    nesses
    0.81
    Act Density 0.051%

    No Known Activations