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

    Neuronpedia

    INDEX
    Explanations

    phrases identifying different literary forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     literature
    -0.21
     Literature
    -0.21
    .appspot
    -0.17
    oven
    -0.16
    æĸĩåѦ
    -0.16
    elow
    -0.15
    ader
    -0.15
    CLS
    -0.14
    emale
    -0.14
    ä½ľåĵģ
    -0.14
    POSITIVE LOGITS
     ek
    0.28
     vill
    0.19
     ha
    0.19
     flash
    0.18
     son
    0.18
     persona
    0.18
     hybrids
    0.17
     tank
    0.17
     journalism
    0.17
    found
    0.17
    Act Density 0.072%

    No Known Activations