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

    Neuronpedia

    INDEX
    Explanations

    words related to contradiction or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to contradictions and oppositional concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.72
     Mehran
    -0.71
    NetMessage
    -0.70
     Tycoon
    -0.68
     Assass
    -0.66
     FSA
    -0.65
     Nanto
    -0.65
     throats
    -0.62
    istically
    -0.62
    eele
    -0.61
    POSITIVE LOGITS
     contra
    1.13
    ption
    1.08
    ptions
    1.08
    ventions
    0.88
    vention
    0.85
    ven
    0.85
    asca
    0.82
    ctr
    0.74
    offensive
    0.74
    xon
    0.74
    Act Density 0.010%

    No Known Activations