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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and phrases indicating exceptions or disagreements in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.56
    UnusedPrivate
    -0.54
    PerformLayout
    -0.53
    AndEndTag
    -0.53
     pleaſure
    -0.50
     فريبيس
    -0.48
     arşivlendi
    -0.48
    ----</
    -0.44
     houſe
    -0.43
     beſt
    -0.42
    POSITIVE LOGITS
     rather
    0.81
    而不是
    0.79
    而非
    0.77
     instead
    0.70
    rather
    0.66
     Rather
    0.65
    Rather
    0.64
     statt
    0.63
     plutôt
    0.63
     anstatt
    0.61
    Act Density 0.432%

    No Known Activations