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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to policies and initiatives aimed at social issues

    oai_token-act-pair · gpt-3.5-turbo

    the word "by" in various contexts indicating methods or means of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igi
    -0.75
    Mine
    -0.71
    raq
    -0.70
    OTAL
    -0.69
    igrate
    -0.68
    atz
    -0.68
    bian
    -0.66
    atl
    -0.62
    atem
    -0.61
    IRE
    -0.61
    POSITIVE LOGITS
     virtue
    1.33
     eliminating
    1.21
     introducing
    1.20
     focusing
    1.19
     adopting
    1.18
     refusing
    1.18
     insisting
    1.17
     providing
    1.16
     emphasizing
    1.16
     offering
    1.16
    Act Density 0.091%

    No Known Activations