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

    Neuronpedia

    INDEX
    Explanations

    words related to estimation or approximation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to approximation or estimation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ous
    -0.93
    icity
    -0.83
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    ographs
    -0.79
    ivity
    -0.78
    ificent
    -0.77
    ienne
    -0.75
    iveness
    -0.75
    esse
    -0.75
    ribution
    -0.71
    POSITIVE LOGITS
     peg
    1.33
    pole
    1.08
     pegged
    0.83
     Peg
    0.83
    asi
    0.77
    fork
    0.74
    glers
    0.73
    entary
    0.72
    hog
    0.70
    OTA
    0.69
    Act Density 0.017%

    No Known Activations