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

    Neuronpedia

    INDEX
    Explanations

    comparative terms indicating elevation or dominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numerusform
    -0.67
     ménages
    -0.67
     fatica
    -0.66
     redé
    -0.66
     Mannschaft
    -0.65
    teman
    -0.65
     Flanagan
    -0.63
     trấn
    -0.61
    MENAFN
    -0.61
    adaptiveStyles
    -0.61
    POSITIVE LOGITS
     higher
    2.01
     Higher
    1.79
     high
    1.77
    higher
    1.77
    Higher
    1.75
     HIGHER
    1.66
    HIGH
    1.65
     HIGH
    1.63
     High
    1.60
    high
    1.56
    Act Density 0.143%

    No Known Activations