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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and questioning or reflective phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    silver
    -0.15
    rian
    -0.14
    vak
    -0.14
     lul
    -0.14
     answers
    -0.14
    llx
    -0.14
    xis
    -0.14
     Division
    -0.14
     imaginative
    -0.14
    orida
    -0.13
    POSITIVE LOGITS
    oger
    0.17
    éĢ¸
    0.17
    avenport
    0.16
    ĽĦ
    0.15
    eking
    0.15
    thane
    0.15
    odont
    0.15
     Bieber
    0.14
    ean
    0.14
    ohon
    0.14
    Act Density 0.033%

    No Known Activations