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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to opinions and attitudes, including surprise, honesty, naturalness, and appropriateness

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing certainty and anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposedly
    -0.68
    æ©Ł
    -0.66
    orf
    -0.64
    urus
    -0.63
     allegedly
    -0.61
    ibility
    -0.58
    Downloadha
    -0.57
     traditions
    -0.57
    raint
    -0.57
    emon
    -0.57
    POSITIVE LOGITS
     someday
    1.04
     tomorrow
    1.01
    morrow
    0.90
     next
    0.89
     forever
    0.79
     soon
    0.78
     sooner
    0.76
     fruitful
    0.74
    next
    0.69
     NEXT
    0.68
    Act Density 0.440%

    No Known Activations