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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     loves
    0.69
    icularly
    0.67
    $$\
    0.67
    calls
    0.64
    ####
    0.64
    standing
    0.62
     calls
    0.62
    EXPORT
    0.62
     chiam
    0.60
    $$
    0.60
    POSITIVE LOGITS
     Regime
    0.86
     slipped
    0.82
     verbally
    0.81
     Stroke
    0.79
     forego
    0.79
     Sistemi
    0.79
     Forensic
    0.79
     verbal
    0.78
     Lí
    0.76
     stirred
    0.76
    Act Density 0.001%

    No Known Activations