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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    saf
    -0.78
    terday
    -0.72
    oscope
    -0.69
    ||
    -0.69
    sense
    -0.66
     Annotations
    -0.65
     constitu
    -0.62
    driver
    -0.61
    IED
    -0.61
    NRS
    -0.60
    POSITIVE LOGITS
     contrace
    0.83
    alde
    0.71
     Schwar
    0.69
    fty
    0.69
    cffff
    0.68
     Orth
    0.68
    arine
    0.66
    ktop
    0.65
     dysph
    0.64
     doub
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.