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

    Neuronpedia

    INDEX
    Explanations

    references to achievements or successes in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ton
    -0.14
    _cmos
    -0.14
    unto
    -0.14
     loose
    -0.14
     whose
    -0.13
    iales
    -0.13
    μοÏĤ
    -0.13
    _tri
    -0.13
    ETING
    -0.13
     touching
    -0.13
    POSITIVE LOGITS
    /null
    0.17
    sworth
    0.17
    nable
    0.17
    breadcrumb
    0.15
     Lawson
    0.15
    .credit
    0.15
    erez
    0.14
    ä¸įäºĨ
    0.14
    obuf
    0.14
    ersed
    0.14
    Act Density 0.087%

    No Known Activations