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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to notable or significant concepts related to society and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -0.60
    ASHINGTON
    -0.56
    ulner
    -0.53
    untarily
    -0.53
    iculty
    -0.52
    owship
    -0.52
    ornia
    -0.51
    rongh
    -0.51
     constitu
    -0.50
    iage
    -0.49
    POSITIVE LOGITS
     coincidence
    0.75
    ?)
    0.67
    ?).
    0.65
    ?),
    0.62
     cynicism
    0.56
     justifies
    0.56
     caveat
    0.55
     understatement
    0.55
     tho
    0.54
     ;)
    0.53
    Act Density 1.142%

    No Known Activations