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

    Neuronpedia

    INDEX
    Explanations

    the name "Viv" and related character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alman
    -0.90
    })));
    -0.89
     Donegal
    -0.86
    RunWith
    -0.85
    存于互联网档案馆
    -0.81
     Scro
    -0.80
     Utt
    -0.79
     transversal
    -0.79
    Cray
    -0.78
     Kanna
    -0.78
    POSITIVE LOGITS
     Sharks
    0.86
     Edwards
    0.82
    Svc
    0.76
     telefoon
    0.74
     devoir
    0.72
    امن
    0.71
     dtype
    0.69
     fullt
    0.69
     sharks
    0.69
    theta
    0.68
    Act Density 1.158%

    No Known Activations