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

    Neuronpedia

    INDEX
    Explanations

    information related to offline activity and merit points

    oai_token-act-pair · gpt-3.5-turbo

    references to online activity and metrics related to user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uten
    -0.76
    ios
    -0.74
    rich
    -0.71
    ands
    -0.67
    andro
    -0.64
    eva
    -0.64
    anders
    -0.64
    eff
    -0.64
    uke
    -0.64
    reet
    -0.63
    POSITIVE LOGITS
    Ire
    0.77
    ãĥª
    0.73
    Els
    0.71
    romeda
    0.71
    THING
    0.70
    ãĥ¼ãĥ³
    0.70
    Merit
    0.70
    acters
    0.69
     ACTIONS
    0.69
    ?????-
    0.69
    Act Density 0.054%

    No Known Activations