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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'Y' being used as a standalone characteristic or name

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the letter "Y"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reper
    -0.76
     destro
    -0.75
    Reviewed
    -0.75
    Accessory
    -0.74
    romeda
    -0.64
    Interstitial
    -0.64
    reatment
    -0.61
    redits
    -0.61
    reated
    -0.58
    uci
    -0.58
    POSITIVE LOGITS
     Y
    3.31
    Y
    2.11
     y
    1.91
     Yo
    1.69
     Ys
    1.55
     Ya
    1.53
     Yam
    1.51
     Ye
    1.49
     Yak
    1.46
     Yen
    1.41
    Act Density 0.018%

    No Known Activations