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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that convey comparisons and contrasts in behavior or morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.58
     répondit
    -0.53
    zval
    -0.50
    WebVitals
    -0.50
    onViewCreated
    -0.49
     isSet
    -0.49
    toThrow
    -0.48
    ClientRect
    -0.48
     personnalisés
    -0.46
    esistenza
    -0.46
    POSITIVE LOGITS
     gente
    0.78
     virtuous
    0.76
     honorable
    0.76
     saint
    0.76
     moral
    0.75
     wholesome
    0.74
     honourable
    0.74
     civilised
    0.73
     gentleman
    0.73
     civilized
    0.71
    Act Density 0.530%

    No Known Activations