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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speculation and possibilities

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate uncertainty or suggest possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.59
    '."
    -0.56
    )].
    -0.52
     branching
    -0.49
    seless
    -0.49
    Materials
    -0.48
     awa
    -0.46
     sacrific
    -0.46
    cember
    -0.46
     hemor
    -0.46
    POSITIVE LOGITS
    htaking
    0.54
    uters
    0.52
     Manafort
    0.51
    lando
    0.49
    abet
    0.48
    steamapps
    0.48
     Pelosi
    0.48
    ilingual
    0.47
    illa
    0.47
    amy
    0.47
    Act Density 1.496%

    No Known Activations