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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     padd
    -0.16
     paddle
    -0.14
    åĬŀ
    -0.14
     vlast
    -0.14
     Fus
    -0.13
    ulos
    -0.13
    /tiny
    -0.13
    uspend
    -0.13
    annis
    -0.13
    ãĥ¼ãĥĨãĤ£
    -0.12
    POSITIVE LOGITS
     ment
    0.48
     Ment
    0.39
     mentor
    0.35
     mentoring
    0.35
     mentors
    0.35
    ment
    0.33
     peer
    0.32
    mentor
    0.31
    _ment
    0.31
    MENT
    0.29
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.