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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¿į
    -0.14
    amarin
    -0.14
    ")));
    -0.14
    _singular
    -0.14
    egrator
    -0.14
    ushima
    -0.14
    LOY
    -0.13
    cky
    -0.13
     jeopardy
    -0.13
    inger
    -0.13
    POSITIVE LOGITS
    chalk
    0.19
     offense
    0.18
     productive
    0.17
    èĨ
    0.16
    productive
    0.15
     Offensive
    0.15
    è¿
    0.15
     Slow
    0.15
     offence
    0.15
     offensive
    0.15
    Act Density 0.231%

    No Known Activations