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

    Neuronpedia

    INDEX
    Explanations

    terms related to rankings and position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to rankings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĥĨãĤ£
    -0.85
    vous
    -0.78
     Nou
    -0.75
     Spiegel
    -0.74
    idem
    -0.69
     Infinite
    -0.67
     Bale
    -0.66
    igne
    -0.66
     Syd
    -0.66
     ¯
    -0.65
    POSITIVE LOGITS
     ranked
    1.00
    ranked
    0.82
    Ranked
    0.81
    inois
    0.81
     ranking
    0.79
    Rank
    0.77
    hyde
    0.74
    ¶æ
    0.72
     bidder
    0.70
    irection
    0.70
    Act Density 0.014%

    No Known Activations