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

    Neuronpedia

    INDEX
    Explanations

    proper names that contain the substring "yd" or "gd"

    oai_token-act-pair · gpt-3.5-turbo

    recurring patterns of the letters "yd" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resolve
    -0.69
    ça
    -0.67
     caution
    -0.67
     deaf
    -0.66
    Xi
    -0.63
     FIRE
    -0.62
    xon
    -0.62
     pity
    -0.61
     perfect
    -0.61
    voy
    -0.61
    POSITIVE LOGITS
    aniel
    1.08
    roxy
    1.04
    roid
    0.98
    rox
    0.96
    essert
    0.96
    ynamic
    0.92
    ynam
    0.92
    yd
    0.90
    ere
    0.90
    iamond
    0.89
    Act Density 0.008%

    No Known Activations