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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequencies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofil
    -0.16
    uur
    -0.15
    omik
    -0.15
    ouri
    -0.15
    ivas
    -0.14
    owan
    -0.14
    olec
    -0.14
    jang
    -0.14
    uji
    -0.14
    ì°
    -0.14
    POSITIVE LOGITS
    rey
    0.20
    grav
    0.14
    isphere
    0.14
    .mob
    0.13
    gravity
    0.13
    é³
    0.13
    .rb
    0.13
    .mc
    0.13
     MC
    0.13
    ryption
    0.13
    Act Density 0.094%

    No Known Activations