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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating conflict or critical situations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceutical
    -0.79
    FTWARE
    -0.63
    bender
    -0.58
    planes
    -0.57
    cert
    -0.57
     motions
    -0.57
    Ts
    -0.55
    alities
    -0.55
    OTHER
    -0.55
    tions
    -0.54
    POSITIVE LOGITS
     least
    1.25
    yp
    1.12
     odds
    1.09
     fault
    1.04
     logger
    1.03
     pains
    1.03
     risk
    1.03
     liberty
    0.97
     variance
    0.94
    onement
    0.93
    Act Density 0.093%

    No Known Activations