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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vibrations
    -0.67
     CITY
    -0.65
    etheless
    -0.65
     rejoice
    -0.63
    loo
    -0.61
    PDATE
    -0.61
     conclud
    -0.60
    ancock
    -0.59
    EVA
    -0.58
     conflic
    -0.58
    POSITIVE LOGITS
    ros
    0.79
    ebra
    0.75
    ãĥĨ
    0.73
    eus
    0.67
    atro
    0.65
    eas
    0.63
    ml
    0.63
    gob
    0.62
    ulu
    0.62
    yre
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.