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

    Neuronpedia

    INDEX
    Explanations

    words indicating legal considerations and liability issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    леж
    -0.15
    isko
    -0.14
    .scalablytyped
    -0.14
    одо
    -0.14
    vero
    -0.13
     Cannot
    -0.13
    mj
    -0.13
    лаÑģÑĤи
    -0.13
    -Sep
    -0.13
    ä¹Ī
    -0.12
    POSITIVE LOGITS
     might
    1.10
     may
    1.09
    might
    0.91
    may
    0.87
     Might
    0.75
     MAY
    0.65
     можеÑĤ
    0.58
    à¸Ńาà¸Ī
    0.55
     peut
    0.54
     могÑĥÑĤ
    0.52
    Act Density 0.800%

    No Known Activations