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

    Neuronpedia

    INDEX
    Explanations

    instances of technical terminology or specialized concepts related to research methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    …
    -1.07
     …
    -1.04
    …”
    -1.00
     “
    -1.00
    “…”
    -0.95
     ‘
    -0.95
    =’
    -0.91
    ”…
    -0.89
    .’
    -0.86
     præ
    -0.86
    POSITIVE LOGITS
    parsedMessage
    1.28
    ...."
    1.12
     ....
    1.07
     .....
    1.05
     NCS
    1.04
    '...
    1.03
    "....
    1.03
     ...'
    1.01
    ...'
    1.00
     !...
    1.00
    Act Density 0.096%

    No Known Activations