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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ...↵↵↵
    -0.20
    ,...↵↵
    -0.19
    ..."
    -0.18
    ...↵↵↵↵
    -0.17
    ...↵↵
    -0.17
    ,...
    -0.16
    ...'
    -0.16
    opard
    -0.16
    tle
    -0.15
     MODIFY
    -0.15
    POSITIVE LOGITS
     .
    0.32
     Hook
    0.23
    Hook
    0.21
     Liam
    0.20
     ..
    0.20
    -hook
    0.19
     /
    0.18
     Dou
    0.18
    _HOOK
    0.18
     .,
    0.18
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.