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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal incidents or formal statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.82
    kefeller
    -0.80
    ornia
    -0.79
    steen
    -0.70
    ensity
    -0.66
     instead
    -0.65
    hower
    -0.64
    aeus
    -0.64
     teamed
    -0.64
    byter
    -0.62
    POSITIVE LOGITS
    catentry
    0.71
     proverbial
    0.67
     bureaucr
    0.66
     phenomena
    0.65
     educators
    0.61
     reviewers
    0.61
     professions
    0.60
     commenters
    0.59
     great
    0.59
    THING
    0.59
    Act Density 0.070%

    No Known Activations