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

    Neuronpedia

    INDEX
    Explanations

    words related to data, medicine, or laws

    oai_token-act-pair · gpt-3.5-turbo

    sentences that use the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.75
     chairs
    -0.68
     Visitors
    -0.67
    wrote
    -0.66
     faces
    -0.64
     haun
    -0.62
     accuses
    -0.61
     Wick
    -0.60
     proposes
    -0.59
     parks
    -0.59
    POSITIVE LOGITS
    nt
    1.02
     definitely
    0.90
     supposed
    0.88
    Ĥİ
    0.87
     not
    0.87
     inherently
    0.85
    senal
    0.85
    olate
    0.84
     likely
    0.84
     indeed
    0.81
    Act Density 0.608%

    No Known Activations