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

    Neuronpedia

    INDEX
    Explanations

    quotations or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.20
     “
    -0.19
     âĢŀ
    -0.17
    lando
    -0.14
    tem
    -0.14
    å¬
    -0.14
     Uncategorized
    -0.14
    “As
    -0.13
    bow
    -0.13
    *
    -0.13
    POSITIVE LOGITS
    s
    0.23
    []"
    0.15
    rzy
    0.15
     ↵↵
    0.15
    ":[{↵
    0.15
    ulen
    0.15
    sav
    0.14
    sik
    0.13
    bsite
    0.13
    oord
    0.13
    Act Density 0.043%

    No Known Activations