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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     G
    -0.46
     préc
    -0.45
     algum
    -0.44
     Q
    -0.43
     braços
    -0.43
     mãos
    -0.43
    ch
    -0.41
    he
    -0.41
     M
    -0.41
    na
    -0.41
    POSITIVE LOGITS
     Савезне
    1.11
     AssemblyCulture
    0.99
    BufferException
    0.99
    NameInMap
    0.95
    AsUp
    0.91
    AndEndTag
    0.89
     mentality
    0.87
    ItemBackground
    0.85
     otomatig
    0.85
    NUMX
    0.85
    Act Density 0.644%

    No Known Activations