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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .man
    -0.08
     hath
    -0.07
    make
    -0.07
     fond
    -0.07
     Ravens
    -0.07
     Argentine
    -0.07
     bon
    -0.07
     pardon
    -0.07
    pieces
    -0.07
     foil
    -0.07
    POSITIVE LOGITS
    .setResult
    0.08
    服务业
    0.07
    _Tree
    0.07
    衄
    0.07
     withObject
    0.07
    abilidad
    0.07
     inadvertently
    0.06
    orThunk
    0.06
     Education
    0.06
    verity
    0.06
    Act Density 0.033%

    No Known Activations