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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation used in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.85
     surla
    -0.69
    <unused43>
    -0.66
    <pad>
    -0.66
    <unused41>
    -0.66
    <unused23>
    -0.66
    <unused42>
    -0.66
    <unused74>
    -0.66
    <unused1>
    -0.66
    <unused20>
    -0.66
    POSITIVE LOGITS
    【
    0.41
    《
    0.39
     Superhosts
    0.35
    　
    0.35
    nowu
    0.35
    สำหรับ
    0.34
    <bos>
    0.34
     《
    0.32
     _
    0.32
     >::
    0.32
    Act Density 0.403%

    No Known Activations