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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Mad" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auf
    -0.19
    yük
    -0.17
    aat
    -0.17
    erce
    -0.17
    aeda
    -0.17
    sı
    -0.16
    ingt
    -0.16
    Å¡ek
    -0.15
    orde
    -0.15
    INGTON
    -0.15
    POSITIVE LOGITS
    agascar
    0.34
    ison
    0.34
    eline
    0.33
    onna
    0.31
    ras
    0.30
    cap
    0.29
    rig
    0.29
    emo
    0.27
    dest
    0.27
    ame
    0.26
    Act Density 0.015%

    No Known Activations