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

    Neuronpedia

    INDEX
    Explanations

    sentences containing the phrase "It's not."

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases denying or dismissing statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.81
    éĥ
    -0.72
    è¿
    -0.71
    åº
    -0.71
    oided
    -0.68
    çļ
    -0.68
    AFP
    -0.68
     Presence
    -0.67
    former
    -0.67
    è¦
    -0.66
    POSITIVE LOGITS
     necessarily
    1.04
    icable
    1.01
    orious
    0.96
     advisable
    0.93
     easy
    0.91
     uncommon
    0.90
    eworthy
    0.89
    hin
    0.89
     raining
    0.85
     exactly
    0.84
    Act Density 0.137%

    No Known Activations