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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation or stating facts

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain affirmations or statements of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    farious
    -0.71
     destro
    -0.69
    asper
    -0.64
    arthy
    -0.63
    emale
    -0.61
    iterranean
    -0.60
    "}],"
    -0.60
    è¦ļéĨĴ
    -0.59
    existent
    -0.59
    ',"
    -0.58
    POSITIVE LOGITS
    cknowled
    0.59
     Warp
    0.50
     Leader
    0.50
     Reck
    0.50
     largeDownload
    0.48
     Reporter
    0.48
     Enemy
    0.46
     Celtics
    0.45
     Yi
    0.45
     Remastered
    0.45
    Act Density 0.503%

    No Known Activations