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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic or formal contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating examples or specific details in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    farious
    -0.71
    roleum
    -0.66
    dinand
    -0.61
    gomery
    -0.61
    umbn
    -0.60
    iership
    -0.60
    arthy
    -0.60
    "—
    -0.57
    ividual
    -0.56
    76561
    -0.56
    POSITIVE LOGITS
     Reply
    0.60
    cknowled
    0.59
     Quote
    0.53
     Winds
    0.50
    cknow
    0.50
     Yi
    0.50
     ye
    0.49
     embodiments
    0.48
     dont
    0.48
     Kills
    0.47
    Act Density 0.454%

    No Known Activations