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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong commitment to a particular cause or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing commitment or dedication to a cause or principle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -1.17
    æĺ
    -0.81
    ults
    -0.81
    igmatic
    -0.72
    Sus
    -0.70
    llo
    -0.70
    soever
    -0.69
    emouth
    -0.69
    acements
    -0.67
    lords
    -0.67
    POSITIVE LOGITS
     preserving
    1.18
     maintaining
    1.06
     ensuring
    1.03
     secrecy
    1.02
     keeping
    1.01
     upholding
    0.97
     achieving
    0.96
     improving
    0.95
     protecting
    0.95
     restoring
    0.94
    Act Density 0.106%

    No Known Activations