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

    Neuronpedia

    INDEX
    Explanations

    specific instances where something is being established or set by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote setting a significant standard or precedent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.79
    utils
    -0.69
    uman
    -0.66
    eral
    -0.62
    akening
    -0.61
    veyard
    -0.61
    iors
    -0.59
    ī
    -0.58
    issance
    -0.57
    inventoryQuantity
    -0.56
    POSITIVE LOGITS
     abl
    1.04
    tle
    0.94
     precedent
    0.86
     precedence
    0.83
    flame
    0.76
     aside
    0.74
     groundwork
    0.74
     sights
    0.73
     apart
    0.72
     FIRE
    0.68
    Act Density 0.128%

    No Known Activations