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

    Neuronpedia

    INDEX
    Explanations

    blocks of comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.85
    twimg
    -0.82
     &___
    -0.81
    AsUp
    -0.73
    Hentet
    -0.70
    endphp
    -0.70
     defaultstate
    -0.70
    enterOuterAlt
    -0.70
    RectangleBorder
    -0.68
    外部リンク
    -0.65
    POSITIVE LOGITS
    tabular
    0.54
    GeneratedMessage
    0.52
    Geplaatst
    0.52
    Diweddarwch
    0.49
    Deal
    0.48
    äch
    0.48
    <blockquote>
    0.48
     Савезне
    0.48
    [toxicity=0]
    0.47
    sch
    0.47
    Act Density 0.074%

    No Known Activations