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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or a new section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.77
     fevere
    -0.75
    __":
    -0.75
     surla
    -0.70
     ſta
    -0.70
     läßt
    -0.68
    ipment
    -0.68
    bitField
    -0.67
    ihnachten
    -0.66
     ſever
    -0.66
    POSITIVE LOGITS
     LGBTQ
    0.63
     contextual
    0.59
     empowering
    0.55
     context
    0.54
     transformative
    0.53
     movimiento
    0.53
     diaspora
    0.53
    ranath
    0.52
     nuanced
    0.50
     feminist
    0.50
    Act Density 0.290%

    No Known Activations