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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acha
    -0.71
    cius
    -0.68
     srf
    -0.67
    ername
    -0.67
     Resources
    -0.67
    ua
    -0.66
    trl
    -0.64
     TTL
    -0.64
    halla
    -0.63
     Honor
    -0.63
    POSITIVE LOGITS
    BD
    0.77
    ...)
    0.70
    âĢ¦)
    0.69
    adapt
    0.67
    tted
    0.66
     sund
    0.65
     bites
    0.63
    fixed
    0.63
     malf
    0.62
    âĪ
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.