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

    Neuronpedia

    INDEX
    Explanations

    unique names or proper nouns related to individuals, places, or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.16
    ucker
    -0.16
    ãĥĥãĥī
    -0.15
    æĪ¸
    -0.14
    shan
    -0.14
    atto
    -0.14
    ñas
    -0.14
    adic
    -0.14
    INST
    -0.14
    ooth
    -0.14
    POSITIVE LOGITS
    ç¯
    0.15
     Flour
    0.15
    -NLS
    0.15
    ères
    0.15
     Calder
    0.14
    adge
    0.14
    лек
    0.14
    _launch
    0.14
    ephy
    0.14
    æĬľ
    0.14
    Act Density 0.071%

    No Known Activations