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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to how actions or events are visibly or noticeably perceived

    oai_token-act-pair · gpt-3.5-turbo

    words describing observable qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.83
    ridge
    -0.79
    quote
    -0.72
    sight
    -0.67
    CAST
    -0.66
    ford
    -0.65
    image
    -0.65
    orously
    -0.65
    lords
    -0.64
    onym
    -0.64
    POSITIVE LOGITS
     visibly
    0.80
     noticeable
    0.79
     audible
    0.78
    Dialogue
    0.73
    Flor
    0.70
     twitch
    0.69
     dysph
    0.66
     Improvement
    0.66
    assadors
    0.66
     noticeably
    0.66
    Act Density 0.020%

    No Known Activations