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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     destro
    -0.73
     mathemat
    -0.68
     è£ıè
    -0.64
    interrupted
    -0.63
     toys
    -0.62
     redes
    -0.61
     dolls
    -0.60
     recommendations
    -0.60
     lever
    -0.59
     expenditures
    -0.59
    POSITIVE LOGITS
    UGH
    0.76
    IDES
    0.76
    VERT
    0.74
    heit
    0.73
    IUM
    0.69
    NER
    0.68
    VAL
    0.67
    TER
    0.67
    ACE
    0.67
    OUGH
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.