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

    Neuronpedia

    INDEX
    Explanations

    sentences containing words related to controversies or arguments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    igslist
    -0.65
     mosqu
    -0.62
     apiece
    -0.61
     misdem
    -0.61
    culus
    -0.61
    »Ĵ
    -0.60
     trailed
    -0.58
     culminated
    -0.58
     respectively
    -0.58
    ppa
    -0.58
    POSITIVE LOGITS
    unless
    0.84
    except
    0.80
     Its
    0.78
    Therefore
    0.78
     Therefore
    0.78
    Its
    0.77
    Picture
    0.69
     :(
    0.68
     doesnt
    0.67
    nor
    0.66
    Act Density 0.638%

    No Known Activations