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

    Neuronpedia

    INDEX
    Explanations

    terms related to cause and effect or the results of actions

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to various types of effects and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pigeon
    -0.77
    mbuds
    -0.69
     Timber
    -0.68
     Alto
    -0.67
    mint
    -0.63
     Dud
    -0.62
    cin
    -0.62
     Patriarch
    -0.61
     Methodist
    -0.60
    antz
    -0.59
    POSITIVE LOGITS
    iveness
    1.27
    uated
    1.19
    ual
    1.15
    uating
    1.06
    ively
    1.05
    ually
    1.04
    uel
    1.01
    bringer
    1.00
    uation
    0.99
    uality
    0.98
    Act Density 0.051%

    No Known Activations