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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing the intensity or degree of an action

    oai_token-act-pair · gpt-3.5-turbo

    strongly critical or intense descriptive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocene
    -0.81
    ession
    -0.77
    itude
    -0.73
    ador
    -0.67
    amas
    -0.67
    ando
    -0.65
     Cause
    -0.65
    orno
    -0.64
    ities
    -0.64
    iggs
    -0.64
    POSITIVE LOGITS
     pursued
    0.95
     criticized
    0.91
     regarded
    0.89
     criticised
    0.87
     tuned
    0.87
     publicized
    0.87
     researched
    0.86
     rewarded
    0.86
     guarded
    0.85
     fought
    0.84
    Act Density 0.043%

    No Known Activations