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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases related to legal standards and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.69
    ResumeLayout
    -0.66
     }(\
    -0.65
    HtmlAttribute
    -0.57
    \\\\
    -0.56
     ch
    -0.56
     \"
    -0.56
    ⎨
    -0.55
     \&
    -0.55
    》（
    -0.55
    POSITIVE LOGITS
     auffi
    0.73
     privatisation
    0.66
     anún
    0.66
     typelib
    0.66
     ་་
    0.64
     enfans
    0.64
     termica
    0.62
     shewn
    0.62
    <bos>
    0.62
    ↵
    0.61
    Act Density 0.748%

    No Known Activations