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

    Neuronpedia

    INDEX
    Explanations

    numeric values or data points in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.47
    ſſung
    -1.43
    <unused74>
    -1.41
    ſicht
    -1.41
    <unused52>
    -1.41
    <unused41>
    -1.41
    <unused14>
    -1.41
    <unused16>
    -1.41
    <unused8>
    -1.41
    [@BOS@]
    -1.41
    POSITIVE LOGITS
    The
    0.59
    I
    0.57
        
    0.53
    But
    0.53
                
    0.52
    2
    0.52
     I
    0.52
            
    0.52
    In
    0.51
                    
    0.50
    Act Density 0.112%

    No Known Activations