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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb 'continue' in various forms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ()]);
    -0.89
     lenker
    -0.89
    TypedDataSet
    -0.88
    }\]
    -0.88
     שוליים
    -0.87
     kasarigan
    -0.87
    dersfield
    -0.86
    })),
    -0.85
    gdx
    -0.85
    Datuak
    -0.81
    POSITIVE LOGITS
     continues
    0.93
     Continues
    0.93
    CONTIN
    0.93
     CONTIN
    0.92
     continue
    0.89
    Continues
    0.88
     continuing
    0.88
     Continue
    0.85
     CONTINUE
    0.85
     fortsetter
    0.84
    Act Density 0.038%

    No Known Activations