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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.62
    los
    -0.58
    ("
    -0.57
    tem
    -0.56
    “
    -0.54
    lem
    -0.52
    "
    -0.51
    lig
    -0.51
    cle
    -0.51
    E
    -0.51
    POSITIVE LOGITS
    __':
    1.57
    __":
    1.45
    SequentialGroup
    1.41
    __':
    1.37
     <=",
    1.36
     الحره
    1.32
     NSCoder
    1.32
    IsMutable
    1.30
    ConstraintMaker
    1.28
     EconPapers
    1.28
    Act Density 0.191%

    No Known Activations