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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and expressions of excitement or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FontWeight
    -0.77
    böz
    -0.76
    ation
    -0.76
    ede
    -0.71
     Rump
    -0.70
    gdx
    -0.70
    "):
    -0.68
    aure
    -0.68
    iNdEx
    -0.67
    Sucesor
    -0.66
    POSITIVE LOGITS
    ?!?
    1.61
    %!
    1.59
    !
    1.43
    !!!!!!
    1.43
    !!!!!!!
    1.42
    ?!?!
    1.42
     !
    1.39
    !"
    1.34
    !!!!!!!!!!
    1.34
    ~!
    1.27
    Act Density 0.077%

    No Known Activations