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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating successful performance or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by adverbs of manner

    np_acts-logits-general · gemini-2.0-flash

    works well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.95
    BeginContext
    -0.85
    InvalidProtocol
    -0.83
     ComVisible
    -0.79
    TagMode
    -0.76
     Normdatei
    -0.76
    InjectAttribute
    -0.76
    RenderAtEndOf
    -0.75
    بوابة
    -0.73
    ValueStyle
    -0.70
    POSITIVE LOGITS
     fine
    0.82
     perfectly
    0.81
     best
    0.80
     well
    0.78
     better
    0.77
     wonders
    0.76
     merveille
    0.72
     bäst
    0.71
     perfect
    0.67
     flawlessly
    0.67
    Act Density 0.128%

    No Known Activations