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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons or equivalences

    oai_token-act-pair · gpt-3.5-turbo

    comparative or relational phrases regarding equality or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encer
    -0.68
    eni
    -0.67
    sort
    -0.64
    azel
    -0.63
    Finish
    -0.62
    eworks
    -0.62
    akeru
    -0.62
    encers
    -0.59
    Soft
    -0.59
    glers
    -0.59
    POSITIVE LOGITS
     ours
    1.60
     hers
    1.45
     theirs
    1.42
     those
    1.31
     yours
    1.24
     mine
    1.23
    those
    1.07
     Those
    0.84
     ones
    0.80
     that
    0.77
    Act Density 0.468%

    No Known Activations