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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating insights, relationships, or connections between elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.79
     Patro
    -0.73
     IMEI
    -0.70
     Huguen
    -0.68
     Anſ
    -0.66
     Mahomet
    -0.66
     Cæsar
    -0.65
     Hopf
    -0.65
     Byz
    -0.63
     hierogly
    -0.62
    POSITIVE LOGITS
     the
    1.33
     these
    0.84
     this
    0.83
     those
    0.80
     their
    0.80
     our
    0.76
    :\/\/
    0.76
     a
    0.70
     your
    0.69
    들이
    0.69
    Act Density 1.654%

    No Known Activations