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

    Neuronpedia

    INDEX
    Explanations

    acronyms related to online games

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty tokens or undefined sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.83
     Coul
    -0.80
    swick
    -0.75
    ku
    -0.72
    patrick
    -0.71
    amus
    -0.70
    ulkan
    -0.69
     Edison
    -0.69
     McCartney
    -0.69
    atchewan
    -0.68
    POSITIVE LOGITS
    ORPG
    1.95
    QB
    1.04
    FG
    1.03
    MM
    0.98
    ITH
    0.88
    ONEY
    0.87
    TP
    0.84
    SE
    0.83
    RM
    0.80
    Ħ¢
    0.78
    Act Density 0.023%

    No Known Activations