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

    Neuronpedia

    INDEX
    Explanations

    code snippets or syntax elements commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etz
    -0.18
    alla
    -0.17
    iros
    -0.17
    noch
    -0.16
    ohn
    -0.15
    ald
    -0.15
    esch
    -0.15
    олом
    -0.14
    neh
    -0.14
    ewe
    -0.14
    POSITIVE LOGITS
    838
    0.18
    283
    0.17
     ÑĢаб
    0.15
    alnız
    0.15
    iminal
    0.14
     ven
    0.14
    ottle
    0.14
    983
    0.14
    íĥķ
    0.14
     Gord
    0.14
    Act Density 0.004%

    No Known Activations