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

    Neuronpedia

    INDEX
    Explanations

    expressions of dissatisfaction and criticism regarding behavior and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cum
    -0.16
    .swing
    -0.15
     neutral
    -0.15
    -neutral
    -0.15
    985
    -0.15
    ys
    -0.15
    umd
    -0.14
    ãĤ«ãĥ«
    -0.14
    bara
    -0.14
    deck
    -0.14
    POSITIVE LOGITS
    wake
    0.16
    λαν
    0.15
    otre
    0.15
     slee
    0.14
    Band
    0.14
    ÐĴÐŀ
    0.13
    (compact
    0.13
    ÙİÙĤ
    0.13
    ATYPE
    0.13
    abbo
    0.13
    Act Density 0.288%

    No Known Activations