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

    Neuronpedia

    INDEX
    Explanations

    text related to voting or decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    definite articles and indications of significant subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ethyl
    -0.71
    methyl
    -0.70
     Aden
    -0.67
    entric
    -0.66
    clusive
    -0.65
    native
    -0.62
    Map
    -0.62
    veland
    -0.62
    arget
    -0.62
    olding
    -0.61
    POSITIVE LOGITS
     last
    0.76
     cumbers
    0.72
     way
    0.71
     wrong
    0.71
    Reviewer
    0.69
     previous
    0.68
     earlier
    0.68
     tune
    0.67
     unnecess
    0.66
     previously
    0.66
    Act Density 0.751%

    No Known Activations