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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and expressions of excitement or emphasis

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

    Exclamations

    np_acts-logits-general · gemini-2.0-flash

    end of emphatic clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ede
    -0.86
    gdx
    -0.82
     Rump
    -0.79
    ation
    -0.79
    iNdEx
    -0.79
    [`
    -0.72
     Wetter
    -0.71
     Rés
    -0.71
    aure
    -0.70
    }`).
    -0.69
    POSITIVE LOGITS
    ?!?
    1.42
    ?!?!
    1.25
    !!!!!!!
    1.09
    %!
    1.07
    !!!!!!
    1.07
     !
    1.07
    !!!!!!!!!!
    1.03
    ~!
    0.96
    !
    0.95
    !!!!!!!!
    0.94
    Act Density 0.076%

    No Known Activations