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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions related to calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Terminal
    -0.16
    AllWindows
    -0.16
    dart
    -0.15
    ijing
    -0.15
     terminal
    -0.15
    era
    -0.14
     Willie
    -0.14
    _CPP
    -0.14
     terminals
    -0.14
    ruba
    -0.14
    POSITIVE LOGITS
     INDIRECT
    0.20
     OFFSET
    0.20
     IF
    0.20
     ROW
    0.20
    Sheet
    0.19
    IF
    0.17
     Sheet
    0.17
    OFFSET
    0.17
     MATCH
    0.17
     rowspan
    0.17
    Act Density 0.002%

    No Known Activations