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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions by considering different factors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluating or assessing options or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellen
    -0.73
    employment
    -0.72
    etheless
    -0.71
    interrupted
    -0.70
    zynski
    -0.67
    esan
    -0.67
    claimed
    -0.65
    ahime
    -0.65
    ades
    -0.62
     Noir
    -0.62
    POSITIVE LOGITS
     weigh
    1.14
     weighing
    0.93
     weights
    0.90
    ighed
    0.86
     weighed
    0.82
     weighs
    0.76
     burdens
    0.73
     scales
    0.73
     heaviest
    0.71
    iless
    0.70
    Act Density 0.024%

    No Known Activations