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

    Neuronpedia

    INDEX
    Explanations

    unformatted or whitespace characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -1.02
    styleType
    -0.95
    </caption>
    -0.90
    Portale
    -0.86
     tuyến
    -0.82
    UnsafeEnabled
    -0.79
     صوتيه
    -0.79
    *-*-
    -0.79
    <bos>
    -0.78
    ;';
    -0.76
    POSITIVE LOGITS
     
    1.72
     
    0.78
     ​
    0.66
    rasco
    0.60
     ​​
    0.60
     Elli
    0.59
    lijkheid
    0.56
     Darmstadt
    0.54
     ****
    0.53
    ardt
    0.52
    Act Density 0.142%

    No Known Activations