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

    Neuronpedia

    INDEX
    Explanations

    names of people, specifically in the context of correspondence or messages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     initComponents
    -0.94
     חיצוניים
    -0.92
    GEBURTSDATUM
    -0.90
     tartalomajánló
    -0.86
     виправивши
    -0.84
     AssemblyVersion
    -0.82
    rungsseite
    -0.82
     للاسماء
    -0.79
    AndEndTag
    -0.79
    cadilly
    -0.78
    POSITIVE LOGITS
    ↵
    0.50
    ↵↵
    0.50
    @
    0.49
    </strong>
    0.47
    ant
    0.44
     @
    0.43
    _
    0.41
    http
    0.40
    if
    0.40
     |
    0.40
    Act Density 0.015%

    No Known Activations