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

    Neuronpedia

    INDEX
    Explanations

    phrases involving exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocarditis
    -0.84
     ROK
    -0.82
    OGND
    -0.78
     }}"></
    -0.77
     onData
    -0.77
     Garnet
    -0.76
     Felicity
    -0.74
     Vesta
    -0.71
     NAC
    -0.71
     Rima
    -0.70
    POSITIVE LOGITS
    Except
    0.97
     except
    0.94
     Except
    0.93
    except
    0.85
     trừ
    0.75
    ostante
    0.73
     EXCEPT
    0.72
    EXCEPT
    0.70
     unless
    0.68
     misst
    0.66
    Act Density 0.096%

    No Known Activations