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

    Neuronpedia

    INDEX
    Explanations

    phrases related to multiple contributing elements or factors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce lists or multiple items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.73
    atorium
    -0.72
    lord
    -0.66
    amus
    -0.65
    cast
    -0.64
    vered
    -0.63
    ulus
    -0.62
    scription
    -0.62
    ppo
    -0.62
    psc
    -0.62
    POSITIVE LOGITS
     including
    1.64
     namely
    1.48
     includ
    1.28
    including
    1.27
     ranging
    1.23
     Including
    1.20
     notably
    1.17
     albeit
    1.16
     depending
    1.14
     viz
    1.06
    Act Density 0.419%

    No Known Activations