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

    Neuronpedia

    INDEX
    Explanations

    URLs and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.68
    lgari
    -0.65
    RenderAtEndOf
    -0.65
     Vikipedi
    -0.65
    expandindo
    -0.64
    StructEnd
    -0.57
    PreferredItem
    -0.56
     Lijst
    -0.56
    orteur
    -0.55
    ArrowToggle
    -0.55
    POSITIVE LOGITS
    ("~/
    0.86
    ={`/
    0.75
    ="/
    0.72
    itoneal
    0.71
     $/
    0.69
    ~/
    0.68
    cgi
    0.67
    httphttps
    0.67
    $/
    0.67
    (`/
    0.66
    Act Density 0.065%

    No Known Activations