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

    Neuronpedia

    INDEX
    Explanations

    words with the prefix "par-" followed by a word starting with a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "par" or "parity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.92
    xia
    -0.82
    ¥µ
    -0.78
    éĹĺ
    -0.73
    doms
    -0.73
    hirt
    -0.73
    æĸ¹
    -0.73
    士
    -0.70
    ;;;;;;;;;;;;
    -0.69
    hower
    -0.67
    POSITIVE LOGITS
    rot
    0.86
     ILCS
    0.83
    allel
    0.81
    agraph
    0.80
    icularly
    0.80
    ret
    0.80
    vati
    0.78
    onto
    0.77
    icy
    0.77
    par
    0.76
    Act Density 0.010%

    No Known Activations