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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rister
    -0.55
     corner
    -0.54
    aarrggbb
    -0.54
     henvisninger
    -0.54
    выше
    -0.50
    hyrchwyd
    -0.50
     rest
    -0.49
     biệt
    -0.48
    ThroughAttribute
    -0.48
     wireType
    -0.48
    POSITIVE LOGITS
    <h3>
    1.33
    <h4>
    1.28
    ↵↵↵
    1.22
    <eos>
    1.17
    <h5>
    1.15
    ↵
    1.10
    <h2>
    1.08
    <h6>
    1.06
    ↵↵↵↵↵
    1.05
    ↵↵↵↵
    1.02
    Act Density 0.017%

    No Known Activations