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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mey
    -0.15
    agem
    -0.15
    aña
    -0.14
     ench
    -0.14
    veau
    -0.14
    foy
    -0.14
    grep
    -0.14
    nde
    -0.14
     إذ
    -0.14
    FFE
    -0.13
    POSITIVE LOGITS
    000
    0.42
    500
    0.29
    600
    0.27
    700
    0.24
    300
    0.24
    800
    0.24
    400
    0.23
    Û°Û°Û°
    0.23
    ooo
    0.22
    900
    0.20
    Act Density 0.071%

    No Known Activations