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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "grab" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    imperative phrases related to taking or seizing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMY
    -0.77
    xual
    -0.73
    MQ
    -0.65
     Prol
    -0.62
    present
    -0.62
     Democr
    -0.61
    SPONSORED
    -0.61
    Correct
    -0.60
     Schwarz
    -0.59
    acre
    -0.59
    POSITIVE LOGITS
    bers
    1.04
    bing
    1.01
    bable
    0.99
     onto
    0.91
    ber
    0.88
    hold
    0.87
     hold
    0.84
    bed
    0.82
     glances
    0.80
    bage
    0.80
    Act Density 0.044%

    No Known Activations