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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles on a particular date

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merga
    -0.67
    houses
    -0.66
    mere
    -0.66
    paper
    -0.65
    conservancy
    -0.64
    natureconservancy
    -0.64
    Cu
    -0.64
    ĺħ
    -0.64
    benef
    -0.64
    perate
    -0.63
    POSITIVE LOGITS
     September
    1.04
     October
    0.98
     August
    0.92
     December
    0.86
     June
    0.85
     July
    0.85
     November
    0.79
     May
    0.76
     April
    0.75
     February
    0.74
    Act Density 0.030%

    No Known Activations