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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific identifiers in the surrounding text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amation
    -0.17
    cloak
    -0.15
    etch
    -0.15
    ãĤ¤ãĥ¤
    -0.15
    μÏĮ
    -0.15
    ctal
    -0.15
    nage
    -0.14
    295
    -0.14
    ãĥ¡ãĥ©
    -0.14
    amura
    -0.14
    POSITIVE LOGITS
    USIC
    0.17
     Perkins
    0.17
     lug
    0.16
    PTS
    0.15
    ilot
    0.14
    &E
    0.14
     infer
    0.13
    rap
    0.13
     Gerard
    0.13
    ulong
    0.13
    Act Density 0.033%

    No Known Activations