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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions not to do something

    oai_token-act-pair · gpt-3.5-turbo

    the word "don't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.68
     pus
    -0.67
     Featured
    -0.61
     afore
    -0.60
    EStream
    -0.59
     Species
    -0.59
    phal
    -0.59
    tnc
    -0.59
     ejected
    -0.59
     DRAGON
    -0.58
    POSITIVE LOGITS
    't
    1.57
    ned
    0.93
    ning
    0.92
    ovan
    0.90
    atives
    0.89
    ÃŃ
    0.88
    ations
    0.87
    ately
    0.87
    uts
    0.86
    orman
    0.86
    Act Density 0.028%

    No Known Activations