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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making and conditional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owitz
    -0.17
    ivec
    -0.17
    razier
    -0.16
    meyi
    -0.15
    é«ĺæ¸ħ
    -0.15
    yük
    -0.15
     olsun
    -0.14
     lạ
    -0.14
    $MESS
    -0.14
    ught
    -0.14
    POSITIVE LOGITS
     cannot
    1.13
    cannot
    0.96
     Cannot
    0.94
    Cannot
    0.85
     cant
    0.82
    ä¸įèĥ½
    0.73
     unable
    0.68
     Cant
    0.66
    æĹłæ³ķ
    0.64
     couldn
    0.62
    Act Density 0.548%

    No Known Activations