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

    Neuronpedia

    INDEX
    Explanations

    code and programming constructs related to vector operations and floating-point arithmetic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "__
    -0.73
    .__
    -0.66
     '__
    -0.64
    "__
    -0.64
    '__
    -0.62
    ).__
    -0.56
    ).*
    -0.56
    )__
    -0.55
    /')
    -0.55
    ("__
    -0.52
    POSITIVE LOGITS
     _
    1.50
     $\
    0.94
    SourceChecksum
    0.69
    _
    0.67
    EndProject
    0.67
    $\
    0.63
    (_
    0.60
     estekak
    0.57
    StoreMessageInfo
    0.55
    }{$\
    0.55
    Act Density 0.117%

    No Known Activations