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

    Neuronpedia

    INDEX
    Explanations

    foreign or non-English terms and characters used in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ£ĭçīĮ
    -0.15
    ursal
    -0.15
    kich
    -0.15
    彦
    -0.15
    rada
    -0.14
    fet
    -0.14
    fait
    -0.14
    chied
    -0.14
    oÅĽci
    -0.14
    apia
    -0.14
    POSITIVE LOGITS
    ï¸ı
    0.18
    ants
    0.16
    uel
    0.15
    er
    0.15
    ampus
    0.15
    -lfs
    0.14
     Pink
    0.14
     elect
    0.14
     Wish
    0.14
    ski
    0.14
    Act Density 0.051%

    No Known Activations