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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and connecting phrases in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.15
    áš
    -0.15
    icha
    -0.15
     puta
    -0.14
    asher
    -0.14
    elli
    -0.14
    érie
    -0.14
    enie
    -0.14
    ób
    -0.13
    idir
    -0.13
    POSITIVE LOGITS
     others
    0.17
    618
    0.17
    ãģĻãģİ
    0.15
     Others
    0.15
     Susp
    0.15
    _strip
    0.14
    gle
    0.14
    838
    0.14
    698
    0.14
    isch
    0.14
    Act Density 0.149%

    No Known Activations