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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and their common constructions in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.71
     igång
    -0.61
     Jacinto
    -0.60
     drey
    -0.60
     habet
    -0.58
     ordina
    -0.58
    OGND
    -0.57
     AMOR
    -0.57
    similar
    -0.57
    InlineData
    -0.56
    POSITIVE LOGITS
     BoxFit
    0.93
     δεν
    0.89
     μην
    0.86
    resizingMask
    0.83
     θα
    0.82
     לא
    0.82
    )$_
    0.80
    avía
    0.80
     MainAxisSize
    0.79
     rospy
    0.79
    Act Density 0.045%

    No Known Activations