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

    Neuronpedia

    INDEX
    Explanations

    references to the start of new sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.95
     (
    -0.93
    :
    -0.89
    ,
    -0.87
     "
    -0.86
     '
    -0.81
    ?
    -0.80
    -
    -0.78
     -
    -0.78
    /
    -0.75
    POSITIVE LOGITS
     itſelf
    1.41
     myſelf
    1.34
     kasarigan
    1.25
     purpoſe
    1.23
     Jefus
    1.21
     ་་
    1.21
     vectorstock
    1.20
     pleaſure
    1.19
     houſe
    1.18
     ſche
    1.16
    Act Density 2.173%

    No Known Activations