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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ranges or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemat
    -0.57
     benef
    -0.56
    reports
    -0.53
    ergic
    -0.53
    aum
    -0.52
     regards
    -0.52
    ubi
    -0.51
    aign
    -0.51
    ippi
    -0.51
    na
    -0.51
    POSITIVE LOGITS
    ggles
    1.05
    pless
    0.95
    pload
    0.90
     insure
    0.85
     compensate
    0.81
     ensure
    0.80
    asted
    0.77
     fend
    0.76
    lling
    0.76
     intensify
    0.75
    Act Density 0.078%

    No Known Activations