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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms of critique or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.17
    acie
    -0.17
    arkin
    -0.16
    ülü
    -0.15
    ANNER
    -0.14
    wd
    -0.14
    essen
    -0.14
     predictable
    -0.13
    ัà¸ķà¸ĸ
    -0.13
    ww
    -0.13
    POSITIVE LOGITS
    ruary
    0.20
    gerald
    0.18
    bruary
    0.16
    odor
    0.15
    auf
    0.15
     Futures
    0.15
    azzi
    0.15
    YPE
    0.15
    .tif
    0.15
     mrb
    0.15
    Act Density 0.110%

    No Known Activations