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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and responsibility expressed with confidence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their contributions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.77
     supposedly
    -0.76
     Written
    -0.73
    irrel
    -0.72
    tumblr
    -0.71
     purportedly
    -0.69
     TMZ
    -0.66
    ultimate
    -0.65
    Advertisements
    -0.65
    Writ
    -0.65
    POSITIVE LOGITS
     anecd
    0.99
     optimism
    0.77
    oqu
    0.77
    mson
    0.74
     expects
    0.72
    heny
    0.72
     optimistic
    0.71
     cautiously
    0.70
    tsky
    0.69
     personally
    0.69
    Act Density 0.567%

    No Known Activations