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

    Neuronpedia

    INDEX
    Explanations

    common phrases starting with "None of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enic
    -0.69
     ancest
    -0.65
    sea
    -0.61
    ogyn
    -0.61
    align
    -0.60
    Preview
    -0.60
    iseum
    -0.59
    acci
    -0.59
     Browse
    -0.59
    tra
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.09
     answers
    0.85
     dime
    0.81
     nor
    0.76
     anymore
    0.76
     guarantees
    0.69
    affles
    0.67
     anything
    0.67
    ife
    0.67
     surprises
    0.66
    Act Density 0.070%

    No Known Activations