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

    Neuronpedia

    INDEX
    Explanations

    the word "lots"

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing abundance or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.73
    robe
    -0.67
    SPONSORED
    -0.67
    oute
    -0.66
     Advocate
    -0.64
    ensis
    -0.61
    agate
    -0.60
    ocard
    -0.60
     Expend
    -0.60
    ufact
    -0.60
    POSITIVE LOGITS
    poons
    0.91
    paces
    0.84
    creen
    0.82
    entimes
    0.80
    tery
    0.77
    hots
    0.77
    ilver
    0.76
    chool
    0.76
    pace
    0.73
    poon
    0.72
    Act Density 0.031%

    No Known Activations