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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to assessing and discussing choices, options, and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.31
     houſe
    -1.31
     myſelf
    -1.28
    ſelf
    -1.26
     Monfieur
    -1.25
     Diſ
    -1.23
     ſeveral
    -1.21
     leaſt
    -1.21
     reaſon
    -1.21
     themſelves
    -1.20
    POSITIVE LOGITS
     
    0.95
    <eos>
    0.93
     of
    0.89
    ,
    0.76
    .
    0.73
    ↵
    0.66
    <bos>
    0.65
     (
    0.60
     to
    0.60
     a
    0.60
    Act Density 1.385%

    No Known Activations