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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different things or situations

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that evaluate or relate two or more subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    he
    -0.71
    iband
    -0.69
    bishop
    -0.66
    arta
    -0.64
    Limited
    -0.63
    Written
    -0.63
    avi
    -0.63
    awar
    -0.62
    vice
    -0.62
    Changed
    -0.61
    POSITIVE LOGITS
     what
    1.07
     other
    1.07
     ours
    1.05
     contemporaries
    1.03
     previous
    1.02
     others
    1.00
     typical
    0.98
     conventional
    0.96
     ordinary
    0.95
     comparable
    0.91
    Act Density 0.139%

    No Known Activations