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

    Neuronpedia

    INDEX
    Explanations

    second person pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases addressing the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uca
    -0.71
    etus
    -0.67
    dimension
    -0.63
     trapping
    -0.63
    ulner
    -0.62
     suspending
    -0.59
    ender
    -0.58
    charging
    -0.58
    abin
    -0.57
    odo
    -0.57
    POSITIVE LOGITS
     guessed
    1.09
     see
    0.97
     know
    0.96
     yourselves
    0.94
     guys
    0.93
     probably
    0.90
     read
    0.89
     remember
    0.89
    're
    0.89
    've
    0.88
    Act Density 0.109%

    No Known Activations