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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pg
    -0.53
    entin
    -0.47
    zech
    -0.47
    iciary
    -0.46
    ingham
    -0.46
    uries
    -0.45
    adelphia
    -0.44
    phabet
    -0.44
     Deity
    -0.43
    ioned
    -0.43
    POSITIVE LOGITS
    urse
    0.54
    ERROR
    0.51
    Reloaded
    0.50
    PUT
    0.49
    paces
    0.49
    message
    0.48
    INFO
    0.48
    CLOSE
    0.48
    FAQ
    0.47
    leave
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.