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

    Neuronpedia

    INDEX
    Explanations

    sections of the text that denote section headers or subsections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.93
    ThroughAttribute
    -0.89
     pleaſure
    -0.85
     jspb
    -0.82
     ProtoMessage
    -0.77
     setShow
    -0.74
    Personendaten
    -0.73
    InitVars
    -0.73
    égories
    -0.73
    astéroïdes
    -0.73
    POSITIVE LOGITS
    <strong>
    0.54
    expandindo
    0.47
    Expedia
    0.46
    </s>
    0.45
    ↵↵↵
    0.44
    </em>
    0.42
    m
    0.42
    n
    0.41
     hilang
    0.40
    چه
    0.38
    Act Density 0.019%

    No Known Activations