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

    Neuronpedia

    INDEX
    Explanations

    unique character symbols or non-standard text representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sez
    -0.15
    ãĥĥãĥĦ
    -0.14
    اÙģر
    -0.14
    ิà¸ĸ
    -0.14
    ç©į
    -0.13
    mia
    -0.13
    eature
    -0.13
    аÑĤегоÑĢ
    -0.13
    _DECLARE
    -0.13
     insists
    -0.13
    POSITIVE LOGITS
     realized
    0.29
     understood
    0.29
     realize
    0.28
     realization
    0.28
     knew
    0.27
     realizing
    0.27
     realizes
    0.26
     realise
    0.24
     realised
    0.24
     understand
    0.23
    Act Density 0.033%

    No Known Activations