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

    Neuronpedia

    INDEX
    Explanations

    occurrences of high-frequency or significant structural elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sokol
    -0.16
    orget
    -0.15
    uma
    -0.15
     waist
    -0.15
    SED
    -0.15
    Overrides
    -0.15
    emiz
    -0.14
    SE
    -0.14
    spb
    -0.14
     zwarte
    -0.14
    POSITIVE LOGITS
    acman
    0.17
    illet
    0.17
    ÑĤеÑĢн
    0.16
     Extr
    0.16
    iff
    0.15
    ancellable
    0.15
    ennie
    0.14
    екÑĤи
    0.14
    yle
    0.14
    ãĥ£
    0.14
    Act Density 0.037%

    No Known Activations