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

    Neuronpedia

    INDEX
    Explanations

    references to prefixes and suffixes in programming or formal definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.49
    Життєпис
    -0.45
     estekak
    -0.44
    OGND
    -0.44
    tagHelperRunner
    -0.43
    ToBounds
    -0.43
    UAWEI
    -0.42
    lwz
    -0.40
     arşivlendi
    -0.40
    +:+
    -0.39
    POSITIVE LOGITS
     prefix
    1.25
    prefix
    1.16
    Prefix
    1.15
     Prefix
    1.09
     prefixes
    1.02
     suffix
    1.00
    Suffix
    1.00
    suffix
    0.95
    PREFIX
    0.93
     PREFIX
    0.87
    Act Density 0.421%

    No Known Activations