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

    Neuronpedia

    INDEX
    Explanations

    comparative adverbs or adjectives

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that emphasize the degree or extent of a quality or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psyche
    -0.63
    ription
    -0.61
     Exhibition
    -0.60
     Library
    -0.58
     caster
    -0.58
     Religion
    -0.57
    agate
    -0.56
     blocker
    -0.56
     proclamation
    -0.56
     Ruler
    -0.55
    POSITIVE LOGITS
     fewer
    0.92
    undreds
    0.84
    limited
    0.83
    zens
    0.79
    idespread
    0.76
    adequ
    0.75
     disparate
    0.74
    zero
    0.74
    appropriate
    0.73
     minimal
    0.73
    Act Density 0.308%

    No Known Activations