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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and expressions associated with programming logic and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emo
    -0.16
     Echo
    -0.15
    ondheim
    -0.14
    raf
    -0.14
    Echo
    -0.14
    abby
    -0.14
    orizontal
    -0.14
     Bald
    -0.13
    942
    -0.13
    Batch
    -0.13
    POSITIVE LOGITS
     signed
    0.27
    overflow
    0.24
     overflow
    0.24
    æº
    0.24
    -signed
    0.23
     Overflow
    0.22
    Overflow
    0.22
     representation
    0.22
     Signed
    0.22
     unsigned
    0.21
    Act Density 0.064%

    No Known Activations