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

    Neuronpedia

    INDEX
    Explanations

    political and governmental terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or metrics related to assessments or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agements
    -0.54
    vernment
    -0.53
    yss
    -0.53
    agers
    -0.53
     curfew
    -0.48
    othing
    -0.47
    otta
    -0.47
     heavier
    -0.46
    arl
    -0.45
    uten
    -0.45
    POSITIVE LOGITS
    ().
    0.69
    _.
    0.64
     Retrieved
    0.62
     https
    0.60
     ().
    0.54
    !.
    0.53
    uesday
    0.52
    youtu
    0.50
    %.
    0.50
    https
    0.49
    Act Density 1.565%

    No Known Activations