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

    Neuronpedia

    INDEX
    Explanations

    statements of existence or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simul
    -0.16
    å¯
    -0.15
    ä¿
    -0.15
    ifndef
    -0.15
    oret
    -0.15
    XS
    -0.15
    roid
    -0.14
    àµįà´
    -0.14
    orte
    -0.14
    azz
    -0.13
    POSITIVE LOGITS
    itzer
    0.15
    ski
    0.15
    Ñľ
    0.14
    _decorator
    0.14
    ring
    0.14
    osos
    0.14
    Utility
    0.14
    даÑı
    0.13
     Sesso
    0.13
    eldon
    0.13
    Act Density 0.286%

    No Known Activations