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

    Neuronpedia

    INDEX
    Explanations

    headers or section titles in academic documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     >=
    -0.52
    <eos>
    -0.50
     Wolfe
    -0.49
    ldorf
    -0.48
    ACHE
    -0.48
    Glej
    -0.48
     glatt
    -0.48
    EMPT
    -0.47
    خم
    -0.47
    uerre
    -0.47
    POSITIVE LOGITS
     poffible
    0.69
     Anſ
    0.68
     Jefus
    0.67
     anſ
    0.62
    DispatchToProps
    0.61
     iprot
    0.61
    harapkan
    0.59
     resourceCulture
    0.59
     通販
    0.58
    انجليز
    0.57
    Act Density 0.016%

    No Known Activations