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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.66
     
    -0.59
    ↵↵
    -0.59
    ↵
    -0.54
     No
    -0.53
     ad
    -0.52
     Don
    -0.51
    ,
    -0.49
     (
    -0.49
    中海
    -0.49
    POSITIVE LOGITS
     myſelf
    1.05
     Majefty
    1.00
     Jefus
    0.97
     Efq
    0.95
     pleaſure
    0.93
    0.93
     Савезне
    0.92
    ſelves
    0.92
     autorytatywna
    0.91
     itſelf
    0.85
    Act Density 0.070%

    No Known Activations