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

    Neuronpedia

    INDEX
    Explanations

    instances of illegal or criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pie
    -0.17
    ovie
    -0.15
    елов
    -0.15
    acock
    -0.15
    essions
    -0.15
    zion
    -0.15
     Cha
    -0.14
    ivism
    -0.14
    åŁ·
    -0.14
    anned
    -0.14
    POSITIVE LOGITS
     ÑĨенÑĤÑĢа
    0.15
    .Emit
    0.15
    uby
    0.14
     Kür
    0.14
    optera
    0.14
    kud
    0.14
    cplusplus
    0.13
    937
    0.13
    871
    0.13
    377
    0.13
    Act Density 0.044%

    No Known Activations