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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ...
    -0.17
     ...(
    -0.17
     ...↵↵
    -0.16
    VC
    -0.15
     shit
    -0.15
    --
    -0.15
    latlong
    -0.14
     ...\
    -0.14
    ereço
    -0.14
    Æ°Æ¡i
    -0.14
    POSITIVE LOGITS
     Alpha
    0.23
    Alpha
    0.18
     ALPHA
    0.18
     Beta
    0.17
     defense
    0.17
     alpha
    0.17
     Defense
    0.16
    -defense
    0.15
     trainer
    0.15
    -vs
    0.15
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.