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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _bonus
    -0.06
     ceremonial
    -0.06
     الأخ
    -0.06
    umbledore
    -0.06
    準
    -0.06
     halk
    -0.06
     ف
    -0.06
    艾
    -0.06
    だって
    -0.06
     trait
    -0.06
    POSITIVE LOGITS
     andre
    0.07
    vlan
    0.07
    inta
    0.06
    archives
    0.06
    Fear
    0.06
     October
    0.06
     (()
    0.06
    وری
    0.06
     messaging
    0.06
    _where
    0.06
    Act Density 0.000%

    No Known Activations