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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or absoluteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.85
    isson
    -0.79
    zie
    -0.79
    åĤ
    -0.77
    beh
    -0.73
    worldly
    -0.72
    oga
    -0.72
    eways
    -0.71
    isure
    -0.70
    gee
    -0.69
    POSITIVE LOGITS
    heartedly
    0.71
     revolves
    0.70
     authentic
    0.67
     transparent
    0.65
     agree
    0.63
     automated
    0.63
     intentional
    0.63
     idiot
    0.63
     assured
    0.63
    rated
    0.62
    Act Density 0.033%

    No Known Activations