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

    Neuronpedia

    INDEX
    Explanations

    mention of individuals holding leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adoes
    -0.66
    âĨij
    -0.64
    ĸļ
    -0.64
    Constructed
    -0.63
    ISM
    -0.62
     autos
    -0.61
     Ink
    -0.61
     Newsp
    -0.61
    eers
    -0.60
     Parenthood
    -0.58
    POSITIVE LOGITS
    quartered
    1.24
    hunter
    1.23
    lining
    1.23
    hun
    1.22
    quarter
    1.13
    liner
    1.13
    quarters
    1.12
    liners
    1.07
    gear
    1.06
    mist
    1.03
    Act Density 0.019%

    No Known Activations