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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations indicative of formal proofs or scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bstract
    -0.16
    Ư
    -0.16
    åĿĬ
    -0.15
    èn
    -0.15
    ubat
    -0.15
    боÑĤ
    -0.15
    oton
    -0.15
    ardy
    -0.14
    kee
    -0.14
    battery
    -0.14
    POSITIVE LOGITS
    153
    0.17
    ersed
    0.16
    ailable
    0.14
    /-
    0.14
    pread
    0.14
    ics
    0.14
    ayi
    0.14
    anda
    0.13
    ÏĤ
    0.13
    æļ
    0.13
    Act Density 0.068%

    No Known Activations