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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to functionality or helpfulness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of usefulness or practicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ran
    -0.76
     Anthem
    -0.76
    istan
    -0.70
    rix
    -0.70
     Pledge
    -0.62
     backdrop
    -0.61
    had
    -0.59
     accuser
    -0.59
     Ocean
    -0.58
     Television
    -0.58
    POSITIVE LOGITS
     useful
    3.35
     helpful
    2.28
     Useful
    2.22
     valuable
    2.08
     usable
    1.96
     handy
    1.91
     usefulness
    1.88
     invaluable
    1.80
     worthwhile
    1.78
     useless
    1.67
    Act Density 0.014%

    No Known Activations