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

    Neuronpedia

    INDEX
    Explanations

    elements indicative of structured data, such as parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entitle
    -0.82
     tack
    -0.71
     tackling
    -0.69
     brigade
    -0.67
     intellig
    -0.67
     overhaul
    -0.67
     galleries
    -0.66
     comparisons
    -0.66
     brig
    -0.65
     decorations
    -0.64
    POSITIVE LOGITS
    ...)
    1.25
    âĢ¦)
    1.16
    possibly
    1.10
    partial
    1.07
    ++)
    1.05
    formerly
    1.05
    Laughs
    1.05
    unsigned
    1.04
    insert
    1.04
    REDACTED
    1.03
    Act Density 0.042%

    No Known Activations