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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific phrases within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oke
    -0.15
    ospace
    -0.14
    hart
    -0.14
    expo
    -0.14
    eyim
    -0.14
    uum
    -0.14
    æķ
    -0.13
    ÑĥÑĢÑĥ
    -0.13
    urs
    -0.13
    ache
    -0.13
    POSITIVE LOGITS
    ainter
    0.15
    iger
    0.15
    iyon
    0.15
    buz
    0.15
    532
    0.14
    mav
    0.13
    ëĭĪìĬ¤
    0.13
     etc
    0.13
    xaf
    0.13
    kili
    0.13
    Act Density 0.323%

    No Known Activations