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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to illnesses and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.60
    roek
    -0.55
     Policing
    -0.53
     Psychotherapy
    -0.52
    olymers
    -0.52
    -0.51
    裟
    -0.51
    djangoproject
    -0.50
    berdayakan
    -0.50
     étrang
    -0.49
    POSITIVE LOGITS
     disease
    1.01
     diseases
    0.94
     infection
    0.92
     illness
    0.86
     virus
    0.82
     epidemic
    0.81
     symptoms
    0.80
    disease
    0.80
     illnesses
    0.80
     ailment
    0.78
    Act Density 0.631%

    No Known Activations