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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or formal matters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eka
    -1.08
     Tale
    -1.03
    EE
    -0.89
    odan
    -0.84
     Topics
    -0.84
    ahime
    -0.83
    orus
    -0.82
     Ou
    -0.81
     accidentally
    -0.80
    hua
    -0.80
    POSITIVE LOGITS
     imaginable
    1.85
     conceivable
    1.55
    except
    1.37
     except
    1.34
     whatsoever
    1.03
    ãĤ«
    1.02
    wcsstore
    1.01
     possible
    0.98
    iev
    0.96
     sane
    0.96
    Act Density 2.213%

    No Known Activations