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

    Neuronpedia

    INDEX
    Explanations

    terms related to the word "level"

    oai_token-act-pair · gpt-3.5-turbo

    the word "lev" and its variations, indicating a focus on levels or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TERN
    -0.81
    SEE
    -0.79
    natureconservancy
    -0.78
    DAY
    -0.74
    ãģ¦
    -0.67
    functional
    -0.66
    luaj
    -0.66
    day
    -0.66
    é¾įå¥ij士
    -0.65
    manship
    -0.64
    POSITIVE LOGITS
    isions
    1.35
    ision
    1.15
    ideos
    1.01
    ski
    0.99
    ille
    0.98
    ideo
    0.98
    iating
    0.95
    iations
    0.95
    iation
    0.95
    ices
    0.93
    Act Density 0.014%

    No Known Activations