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

    Neuronpedia

    INDEX
    Explanations

    negations and terms indicating the absence or restriction of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GRAP
    -0.69
    IMENTAL
    -0.68
      
    -0.67
    `,
    -0.64
     
    -0.62
    VELOP
    -0.61
    ∘
    -0.61
    writeField
    -0.60
     TRAV
    -0.60
    aday
    -0.60
    POSITIVE LOGITS
     BOTH
    1.59
     ANY
    1.56
     ONLY
    1.55
     HUGE
    1.52
     FREE
    1.46
     NEVER
    1.43
     NOT
    1.42
     ALL
    1.42
     ANYONE
    1.41
     VERY
    1.39
    Act Density 0.199%

    No Known Activations