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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and whitespace related to article titles or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovic
    -0.16
     Ariel
    -0.15
     CES
    -0.15
     MATRIX
    -0.14
    atik
    -0.14
    ì°©
    -0.14
    athi
    -0.14
    arrass
    -0.14
    ahu
    -0.14
    ustum
    -0.14
    POSITIVE LOGITS
     Tan
    0.21
     season
    0.21
     Demon
    0.19
     tan
    0.18
    Tan
    0.17
     Season
    0.17
     Bor
    0.17
    lingen
    0.16
    season
    0.16
     Nez
    0.16
    Act Density 0.001%

    No Known Activations