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

    Neuronpedia

    INDEX
    Explanations

    citations and references to scientific sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vej
    -0.16
    auses
    -0.15
    AlgorithmException
    -0.15
    ạt
    -0.14
    avanaugh
    -0.14
    _SECTION
    -0.14
    ersions
    -0.13
    /trunk
    -0.13
     fis
    -0.13
    ñana
    -0.13
    POSITIVE LOGITS
    alf
    0.17
    als
    0.16
    path
    0.15
    undef
    0.15
    oub
    0.15
    peng
    0.15
    irl
    0.15
    autop
    0.14
    alt
    0.14
     interviews
    0.14
    Act Density 0.025%

    No Known Activations