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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "strong" together with a specific noun

    oai_token-act-pair · gpt-3.5-turbo

    the substring "ong"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABE
    -0.70
     NASCAR
    -0.69
    ãĥ¤
    -0.66
    perature
    -0.64
    代
    -0.64
     McA
    -0.63
     GOODMAN
    -0.63
     Quadro
    -0.63
     Goat
    -0.61
     CoC
    -0.60
    POSITIVE LOGITS
    ratulations
    1.28
    regate
    1.13
    regor
    1.01
    vernment
    0.97
    lass
    0.92
    lasses
    0.91
    uay
    0.91
    jiang
    0.89
    atana
    0.87
    ueless
    0.83
    Act Density 0.019%

    No Known Activations