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

    Neuronpedia

    INDEX
    Explanations

    references to exceptions in rules or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shake
    -0.15
    manship
    -0.15
    iaux
    -0.15
    slick
    -0.14
    agra
    -0.14
    isha
    -0.14
    iske
    -0.14
    lek
    -0.13
    ona
    -0.13
    LETE
    -0.13
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.20
    ively
    0.17
     Schwar
    0.15
    ually
    0.15
    aldi
    0.15
    ities
    0.15
     ìĤ¬íķŃ
    0.15
    éĻħ
    0.14
    swith
    0.14
    ably
    0.14
    Act Density 0.026%

    No Known Activations