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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing intense qualities, such as 'such a' or 'of a'

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating strong emphasis or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endi
    -0.75
    ids
    -0.75
    seys
    -0.74
    aired
    -0.70
    onds
    -0.69
    rones
    -0.65
    pta
    -0.64
    urb
    -0.63
    reys
    -0.63
    earance
    -0.63
    POSITIVE LOGITS
     fun
    1.02
     hassle
    0.94
     nightmare
    0.87
     fodder
    0.83
     gamble
    0.83
     annoyance
    0.83
     embarrassment
    0.82
    cule
    0.82
     nuisance
    0.82
     sleeper
    0.78
    Act Density 0.069%

    No Known Activations