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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cano
    -0.72
    soever
    -0.65
     confir
    -0.63
    ython
    -0.62
    withstanding
    -0.62
     resear
    -0.62
     stret
    -0.61
     invent
    -0.61
     granting
    -0.61
     deliberations
    -0.60
    POSITIVE LOGITS
     Correction
    0.71
    adelphia
    0.69
    Virgin
    0.69
    women
    0.68
    teness
    0.66
    ersion
    0.66
    istor
    0.64
    URA
    0.64
    enture
    0.64
    arie
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.