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

    Neuronpedia

    INDEX
    Explanations

    references to medical study results and comparisons between different patient groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.64
    …
    -0.56
    ..
    -0.56
    ...
    -0.52
    ).
    -0.46
     descon
    -0.46
    ….
    -0.45
    .)
    -0.44
     su
    -0.41
    ....
    -0.40
    POSITIVE LOGITS
     Jefus
    1.09
     Efq
    1.04
     Monfieur
    0.99
     nakalista
    0.98
     myſelf
    0.94
     itſelf
    0.94
     Houſe
    0.93
     becauſe
    0.92
     utafitiHapana
    0.91
     Мексичка
    0.90
    Act Density 0.323%

    No Known Activations