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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     just
    -1.27
    After
    -1.21
     what
    -1.17
    Although
    -1.16
    While
    -1.16
    During
    -1.12
     that
    -1.10
     after
    -1.06
    Since
    -1.06
     substantial
    -1.02
    POSITIVE LOGITS
     debacle
    1.21
     horrid
    1.20
     flamboyant
    1.15
     deliciously
    1.15
     ridiculously
    1.14
     tumultuous
    1.13
     strikingly
    1.10
     alluring
    1.10
     delightfully
    1.10
    ︲
    1.09
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.