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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    vals
    -0.72
    bors
    -0.69
    âĢİ
    -0.64
    tt
    -0.64
    kees
    -0.64
     serv
    -0.62
     Boyle
    -0.62
     Buenos
    -0.62
    fer
    -0.61
    jas
    -0.60
    POSITIVE LOGITS
    ĪĴ
    0.86
    awaru
    0.77
    ilage
    0.77
     outwe
    0.73
    ento
    0.67
    SPONSORED
    0.65
    çīĪ
    0.64
     srfAttach
    0.64
     incent
    0.63
     swallow
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.