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

    Neuronpedia

    INDEX
    Explanations

    key terms related to processes and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urances
    -0.15
    Ïħν
    -0.14
    .av
    -0.14
    æ²¢
    -0.14
     DSM
    -0.14
     bulk
    -0.14
    ãĥ¼ãĥĭ
    -0.14
    äter
    -0.14
    ormal
    -0.13
    icaret
    -0.13
    POSITIVE LOGITS
    vik
    0.16
    Ãło
    0.15
    _FLOAT
    0.14
    irie
    0.14
    ELLOW
    0.14
    izu
    0.14
    antine
    0.14
    raman
    0.14
    rou
    0.14
    åł
    0.13
    Act Density 0.012%

    No Known Activations