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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aylor
    -0.17
    ngen
    -0.16
    iola
    -0.15
     Twist
    -0.15
    imos
    -0.15
    ograms
    -0.14
    adata
    -0.14
    ahat
    -0.14
    lando
    -0.14
     Deferred
    -0.14
    POSITIVE LOGITS
    ELLOW
    0.16
    iface
    0.14
    ProcAddress
    0.14
     filetype
    0.13
    неÑĤ
    0.13
    _UNUSED
    0.13
    igh
    0.13
    ileÅŁ
    0.13
     disg
    0.13
    /std
    0.13
    Act Density 0.028%

    No Known Activations