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

    Neuronpedia

    INDEX
    Explanations

    references to technology-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    discussions about relationships and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ðŁ
    -0.73
     âĻ
    -0.67
    ®,
    -0.63
     ðŁij
    -0.60
     rapist
    -0.60
    âĢ
    -0.59
     âĿ
    -0.57
     âĺ
    -0.57
    ðŁ
    -0.57
     âĸ
    -0.57
    POSITIVE LOGITS
     narrower
    0.98
    altern
    0.85
     quieter
    0.82
    different
    0.82
     smaller
    0.80
     slower
    0.79
    illary
    0.79
    arser
    0.78
     weaker
    0.78
     additional
    0.78
    Act Density 1.263%

    No Known Activations