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

    Neuronpedia

    INDEX
    Explanations

    adjectives with strong emotional connotations or ethical significance

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to ethical, offensive, and revolutionary concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orah
    -0.74
    udeb
    -0.70
    region
    -0.69
    onde
    -0.67
    onds
    -0.66
    essage
    -0.66
    adobe
    -0.64
    ournal
    -0.64
    ogie
    -0.64
    secution
    -0.63
    POSITIVE LOGITS
     enough
    1.12
     insofar
    0.79
     fodder
    0.78
     nonetheless
    0.77
     Enough
    0.76
    isable
    0.75
     deterrent
    0.74
    istically
    0.74
    enough
    0.72
     undermin
    0.72
    Act Density 0.469%

    No Known Activations