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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal and philosophical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enis
    -0.16
    ollo
    -0.15
    ÄĽtÅ¡
    -0.15
    ī´
    -0.14
    663
    -0.14
    jang
    -0.14
    772
    -0.14
     fisse
    -0.14
    olygon
    -0.14
    iage
    -0.14
    POSITIVE LOGITS
     Sark
    0.18
     blackmail
    0.17
     States
    0.17
     structural
    0.17
     Macron
    0.16
     Structural
    0.16
     specular
    0.16
     dramas
    0.16
     vert
    0.15
     volunt
    0.15
    Act Density 0.177%

    No Known Activations