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

    Neuronpedia

    INDEX
    Explanations

    words that indicate conditions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REATE
    -0.17
    opensource
    -0.14
    ıcı
    -0.14
    inant
    -0.14
    ENCIL
    -0.13
    izer
    -0.13
    WithURL
    -0.13
    ॰
    -0.13
    ocache
    -0.13
    odash
    -0.13
    POSITIVE LOGITS
     sure
    0.29
     guaranteed
    0.24
     reason
    0.23
    sure
    0.22
     enough
    0.22
     anything
    0.22
     Sure
    0.21
    Sure
    0.20
     bound
    0.19
     unlike
    0.19
    Act Density 0.201%

    No Known Activations