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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of obligation or requirement

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ماً
    -0.68
    osten
    -0.60
    vertre
    -0.59
    vador
    -0.58
     sey
    -0.58
     ~(
    -0.57
    ={()
    -0.57
    injection
    -0.57
     Visconti
    -0.57
    tims
    -0.57
    POSITIVE LOGITS
    المناصب
    0.85
     rospy
    0.82
    rizona
    0.81
    ########.
    0.73
     Heuer
    0.72
    RuleContext
    0.70
    copg
    0.69
    »։
    0.69
    FieldNumber
    0.68
    thâu
    0.68
    Act Density 0.019%

    No Known Activations