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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desires, preferences, or personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &[
    -0.56
     MainAxisSize
    -0.52
    ส์
    -0.51
     derniers
    -0.48
     transfieras
    -0.48
    hynch
    -0.47
     peur
    -0.46
    (&:
    -0.46
     quanto
    -0.45
    abank
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.80
     للمعارف
    0.80
    Референце
    0.64
    Lähteet
    0.63
    preferably
    0.63
     seeing
    0.61
    Ideally
    0.60
    0.60
    assertIn
    0.60
    anskje
    0.60
    Act Density 0.079%

    No Known Activations