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

    Neuronpedia

    INDEX
    Explanations

    emphatic expressions of approval or admiration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enthusiasm or strong support for various subjects, including products, people, and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scarcely
    -0.85
     inevitably
    -0.79
     decidedly
    -0.77
     sufficiently
    -0.75
     abruptly
    -0.74
     predictably
    -0.74
     plaus
    -0.72
     âī¥
    -0.72
     faintly
    -0.72
     faint
    -0.71
    POSITIVE LOGITS
    yss
    0.70
    etts
    0.61
    custom
    0.57
     HERE
    0.56
    elvet
    0.56
    english
    0.56
    senal
    0.56
     teamwork
    0.55
     util
    0.55
    pps
    0.55
    Act Density 0.965%

    No Known Activations