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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ويكيميديا
    -0.34
     Matters
    -0.33
     saker
    -0.32
    ACHUSET
    -0.32
     caminhada
    -0.31
     البعض
    -0.31
     massima
    -0.30
    adaptiveStyles
    -0.30
    UrlResolution
    -0.30
    Jegyzetek
    -0.30
    POSITIVE LOGITS
     clue
    0.95
     protoimpl
    0.72
     excuse
    0.68
    clue
    0.68
     choice
    0.67
     rhyme
    0.66
     earthly
    0.63
     Clue
    0.63
     scrup
    0.63
     patience
    0.63
    Act Density 0.384%

    No Known Activations