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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating risk or negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.49
    SerializedSize
    -0.49
    basePath
    -0.47
    WireFormatLite
    -0.47
    DotNetBar
    -0.46
    ္
    -0.44
     matter
    -0.43
    bieron
    -0.43
    acán
    -0.43
    بيرة
    -0.43
    POSITIVE LOGITS
     :-(
    0.77
     unfortunately
    0.74
    🙁
    0.70
     🤦
    0.69
     :'(
    0.68
     entanto
    0.68
     :(
    0.67
     -_-
    0.67
     оригіналу
    0.67
     niestety
    0.65
    Act Density 1.432%

    No Known Activations