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

    Neuronpedia

    INDEX
    Explanations

    references to statistical journals and related academic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.18
     Efq
    -1.17
     myſelf
    -1.16
     $_"
    -1.14
     ſy
    -1.12
     ་་
    -1.08
     itſelf
    -1.08
    ſelf
    -1.04
     Jefus
    -1.00
     Theſe
    -1.00
    POSITIVE LOGITS
     et
    0.71
     [
    0.69
     
    0.68
     (
    0.68
     -
    0.65
    <eos>
    0.62
    .,
    0.60
     \
    0.59
     ,
    0.58
     D
    0.57
    Act Density 0.455%

    No Known Activations