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

    Neuronpedia

    INDEX
    Explanations

    locations such as parks, cities, and studios

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.56
     betweenstory
    -0.52
     utafitiHapana
    -0.50
    )_/¯
    -0.50
     bezeichneter
    -0.46
    parsedMessage
    -0.44
    ArrowToggle
    -0.44
    UnusedPrivate
    -0.44
     ویکی‌پدیای
    -0.43
    writeFieldEnd
    -0.42
    POSITIVE LOGITS
     Lmao
    0.63
    Fuckin
    0.60
     lmfao
    0.59
    Xoxo
    0.58
     🤣🤣
    0.57
     minValue
    0.56
    Bullshit
    0.56
     😭😭
    0.56
     !...
    0.54
     Wtf
    0.54
    Act Density 0.137%

    No Known Activations