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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of doubt or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numberOfRows
    -0.57
    ête
    -0.50
    Javadoc
    -0.49
     defStyleAttr
    -0.49
    welling
    -0.49
    ależ
    -0.48
    RUnlock
    -0.48
     Peres
    -0.47
    courseId
    -0.47
    덕
    -0.47
    POSITIVE LOGITS
    enumi
    0.68
    хьтан
    0.63
    참고
    0.62
     Приступљено
    0.61
     überhaupt
    0.60
    posedge
    0.57
    مصادر
    0.57
     незавершена
    0.56
     vůbec
    0.56
    ArrowToggle
    0.54
    Act Density 0.639%

    No Known Activations