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

    Neuronpedia

    INDEX
    Explanations

    phrases that express complex ideas or rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trotzdem
    -0.73
     entanto
    -0.68
     nonetheless
    -0.68
     inoltre
    -0.66
    μως
    -0.65
     nevertheless
    -0.65
     moreover
    -0.64
     therefore
    -0.64
     also
    -0.62
     but
    -0.62
    POSITIVE LOGITS
     Well
    2.06
    Well
    2.03
     well
    1.96
    well
    1.77
     WELL
    1.49
    WELL
    1.46
    Pues
    1.14
     Pues
    1.07
     Hmm
    1.01
     Umm
    1.00
    Act Density 0.334%

    No Known Activations