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

    Neuronpedia

    INDEX
    Explanations

    connections between numeric values and their contextual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illian
    -0.16
    celik
    -0.16
    ÙĨز
    -0.15
     ?><?
    -0.14
    æ
    -0.14
    illac
    -0.14
     شب
    -0.14
    itar
    -0.14
    ifax
    -0.14
    tu
    -0.14
    POSITIVE LOGITS
    sworth
    0.19
    olan
    0.18
    akers
    0.16
    oble
    0.15
     Rol
    0.15
    isto
    0.15
    ritt
    0.14
    uya
    0.14
     sk
    0.14
    eron
    0.14
    Act Density 0.196%

    No Known Activations