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

    Neuronpedia

    INDEX
    Explanations

    characters involved in criminal activities or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asan
    -0.16
    Ä©nh
    -0.16
    ansi
    -0.15
     imper
    -0.15
    asad
    -0.14
    andon
    -0.14
     Buckley
    -0.14
    ajs
    -0.14
    .lesson
    -0.14
     cow
    -0.14
    POSITIVE LOGITS
    thora
    0.15
    ê°IJ
    0.14
     Monument
    0.14
    oji
    0.14
    engo
    0.14
    atus
    0.14
     Ard
    0.14
    ë´ī
    0.14
    estatus
    0.14
    ế
    0.13
    Act Density 0.096%

    No Known Activations