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

    Neuronpedia

    INDEX
    Explanations

    symbols that indicate structure or formatting within written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.99
     ProtoMessage
    -0.93
     ExecuteAsync
    -0.89
     kasarigan
    -0.89
    IsMutable
    -0.88
     queſta
    -0.88
    ſchaft
    -0.84
    DeleteBehavior
    -0.81
    -0.81
     ब्रेकडाउन
    -0.81
    POSITIVE LOGITS
    I
    0.48
    [toxicity=0]
    0.45
    The
    0.42
        
    0.41
    //
    0.40
            
    0.40
     
    0.38
    You
    0.37
     nghị
    0.37
                
    0.37
    Act Density 0.531%

    No Known Activations