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

    Neuronpedia

    INDEX
    Explanations

    instances of document structure and conclusion markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.79
     BEGIN
    -0.78
     begin
    -0.78
     begins
    -0.76
    Климат
    -0.74
    хьтан
    -0.71
     هيا
    -0.70
    Begin
    -0.70
     Begin
    -0.67
     begun
    -0.66
    POSITIVE LOGITS
    end
    2.10
    END
    1.39
    End
    1.37
     End
    1.25
     end
    1.12
    ends
    1.11
     END
    1.10
    ending
    0.98
    ended
    0.95
    endos
    0.83
    Act Density 0.039%

    No Known Activations