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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     accord
    1.33
     Darstellung
    1.01
     Trevelyan
    1.01
     congenial
    1.00
     μας
    0.99
     crisp
    0.99
     briefed
    0.97
     insisted
    0.96
     dissident
    0.96
    惇
    0.95
    POSITIVE LOGITS
    Fury
    1.22
    Suc
    1.16
    Sad
    1.15
    vmin
    1.14
    Severe
    1.12
    TN
    1.12
    ehicle
    1.10
     `<=`
    1.09
    mast
    1.09
    Shock
    1.08
    Act Density 0.000%

    No Known Activations