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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ragaz
    -0.17
     eux
    -0.15
    ká
    -0.15
    yas
    -0.14
    reon
    -0.14
    .mvc
    -0.14
    rosse
    -0.14
    AppState
    -0.13
    rch
    -0.13
    öm
    -0.13
    POSITIVE LOGITS
     there
    0.29
     we
    0.25
    there
    0.23
     ÙģØ¥ÙĨ
    0.23
     thì
    0.20
    we
    0.19
     it
    0.18
     they
    0.17
     Ø¥ÙĦا
    0.16
    this
    0.16
    Act Density 0.518%

    No Known Activations