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

    Neuronpedia

    INDEX
    Explanations

    words related to collecting or bringing together different items or data points

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggregation and sourness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agne
    -0.85
    @#&
    -0.79
    DCS
    -0.67
    oses
    -0.67
    oning
    -0.65
    inct
    -0.65
    IELD
    -0.64
     Hemp
    -0.64
    rones
    -0.64
     Mech
    -0.63
    POSITIVE LOGITS
    ging
    0.91
    pillar
    0.78
    die
    0.78
    ities
    0.77
    gew
    0.77
    gers
    0.76
    ged
    0.76
    ulative
    0.76
    umbers
    0.74
    cery
    0.73
    Act Density 0.070%

    No Known Activations