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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional or alternative phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.65
    expandindo
    -0.63
    ताओं
    -0.60
     chng
    -0.60
    ніципалі
    -0.59
    neuf
    -0.57
    SequentialGroup
    -0.57
    fromnode
    -0.56
    cope
    -0.55
     上衣
    -0.55
    POSITIVE LOGITS
    verwijspagina
    0.56
     EconPapers
    0.55
    Geplaatst
    0.54
    zerland
    0.52
    DoubleQuotes
    0.52
    期刊论文
    0.50
    uterte
    0.50
    WireFormat
    0.49
    rabbit
    0.49
    Obrázky
    0.48
    Act Density 0.148%

    No Known Activations