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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions or feelings

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

    "So" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    so adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    较大
    -0.49
     too
    -0.47
    íše
    -0.46
     тоже
    -0.46
    roves
    -0.44
    rror
    -0.43
     élevées
    -0.43
     Largest
    -0.43
    ত্ত
    -0.43
    kitan
    -0.43
    POSITIVE LOGITS
     unbelievably
    0.94
     darn
    0.89
     damn
    0.89
     freaking
    0.85
     incredibly
    0.84
     freakin
    0.82
     damned
    0.82
     wonderfully
    0.81
     amazingly
    0.80
     stink
    0.80
    Act Density 0.066%

    No Known Activations