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

    Neuronpedia

    INDEX
    Explanations

    negations

    oai_token-act-pair · gpt-3.5-turbo

    negations or denials in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.71
    */(
    -0.62
    iferation
    -0.61
    oided
    -0.60
    ittle
    -0.60
    omm
    -0.58
    imentary
    -0.57
    velt
    -0.57
    iber
    -0.56
     fixme
    -0.56
    POSITIVE LOGITS
    etheless
    0.87
     deter
    0.77
     necessarily
    0.72
     entirely
    0.69
     exactly
    0.67
    rael
    0.66
     fooled
    0.65
    ravings
    0.63
     altogether
    0.63
     swayed
    0.61
    Act Density 0.218%

    No Known Activations