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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìķ¼
    -0.15
    abela
    -0.15
    ij
    -0.14
    vor
    -0.14
    .synthetic
    -0.14
     Wagner
    -0.14
     ime
    -0.14
    rij
    -0.14
    kovi
    -0.13
    çµIJå©ļ
    -0.13
    POSITIVE LOGITS
    akens
    0.16
    èĨ
    0.15
    irtual
    0.15
    amen
    0.14
    661
    0.14
    atty
    0.14
     miêu
    0.14
    chantment
    0.14
     g
    0.14
    erton
    0.14
    Act Density 0.050%

    No Known Activations