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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     jot
    -0.07
    .username
    -0.07
    𨺙
    -0.07
     weaker
    -0.07
     nuest
    -0.07
     cons
    -0.07
    顺着
    -0.06
     receive
    -0.06
     stutter
    -0.06
    -a
    -0.06
    POSITIVE LOGITS
    ajax
    0.07
    INTR
    0.07
    _ACTIVE
    0.07
    Keys
    0.07
    ソン
    0.07
    Reason
    0.06
     Rad
    0.06
     ql
    0.06
    payments
    0.06
    ראל
    0.06
    Act Density 0.146%

    No Known Activations