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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    sentences that assert facts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.67
     IMAGES
    -0.67
    bies
    -0.67
     Bung
    -0.66
     congr
    -0.63
     bunch
    -0.63
     Lack
    -0.58
     coasts
    -0.58
     Wish
    -0.58
    itcher
    -0.58
    POSITIVE LOGITS
     unclear
    1.05
     unlikely
    0.99
     impossible
    0.96
    nt
    0.95
     imperative
    0.93
     doubtful
    0.92
     easier
    0.91
    Ĥİ
    0.91
     abundantly
    0.90
     easy
    0.89
    Act Density 0.137%

    No Known Activations