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

    Neuronpedia

    INDEX
    Explanations

    instances of negation in opinions or statements about policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.65
     themſelves
    -0.61
    displayquote
    -0.59
    }{*}{
    -0.57
     ejus
    -0.55
     whoſe
    -0.54
     &___
    -0.54
    astéroïdes
    -0.54
    %@",
    -0.54
     vettor
    -0.54
    POSITIVE LOGITS
    ništ
    0.60
     Okay
    0.57
    SourceChecksum
    0.55
     Commencez
    0.54
    '
    0.54
    Okay
    0.53
    XmlAccessType
    0.53
     ***!
    0.52
     Erişim
    0.51
    Зноскі
    0.50
    Act Density 0.052%

    No Known Activations