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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating a high degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate degree or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pherd
    -0.73
     Registry
    -0.66
     dome
    -0.65
     Plugin
    -0.61
     Arena
    -0.61
     Carnival
    -0.60
     Register
    -0.60
     catcher
    -0.60
     Religion
    -0.59
    iliate
    -0.59
    POSITIVE LOGITS
     incrim
    0.76
    undreds
    0.74
     disparate
    0.73
    zero
    0.73
     amounts
    0.72
    technical
    0.72
     quantities
    0.72
    days
    0.71
     fewer
    0.70
    optim
    0.68
    Act Density 0.267%

    No Known Activations