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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or opinions expressed in first person with a focus on time or developments over time

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating personal perspectives or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.73
    ingham
    -0.63
     Clarks
    -0.56
    pedia
    -0.56
    EVA
    -0.55
    ¢
    -0.54
     Recommend
    -0.53
    orthy
    -0.53
     Tomorrow
    -0.52
    iland
    -0.52
    POSITIVE LOGITS
     actually
    0.80
     ALWAYS
    0.80
     REALLY
    0.79
     exceedingly
    0.79
    nt
    0.76
     disproportionately
    0.75
     rarely
    0.71
     VERY
    0.71
     nowhere
    0.71
     seldom
    0.70
    Act Density 0.806%

    No Known Activations