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

    Neuronpedia

    INDEX
    Explanations

    key numerical values and metrics related to performance and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    满
    -0.17
    滿
    -0.16
    //{{
    -0.16
    berapa
    -0.16
    cü
    -0.15
    urar
    -0.15
    _framework
    -0.15
    åIJĮæŃ¥
    -0.15
    ARAM
    -0.15
    ££
    -0.15
    POSITIVE LOGITS
    ain
    0.18
     Rath
    0.15
     ca
    0.15
     Tooth
    0.15
    iam
    0.15
    ds
    0.14
     nail
    0.14
    inas
    0.14
    ause
    0.14
     Raj
    0.14
    Act Density 0.156%

    No Known Activations