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

    Neuronpedia

    INDEX
    Explanations

    values associated with key-value pairs, specifically in a structured data format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.96
     beginnetje
    -0.83
    expandindo
    -0.79
     незавершена
    -0.77
    ▬▬▬▬▬▬▬▬
    -0.73
     HasFactory
    -0.72
    transQ
    -0.71
     bezeichneter
    -0.67
    
    -0.64
     henvisninger
    -0.63
    POSITIVE LOGITS
     sylla
    0.59
    λιά
    0.56
    หวัด
    0.56
     Syl
    0.56
    endphp
    0.55
     GlobalKey
    0.55
    ็จ
    0.54
    mobileqq
    0.54
    iloto
    0.54
     clothe
    0.53
    Act Density 0.035%

    No Known Activations