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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bez
    -0.14
     Trom
    -0.14
     pres
    -0.14
    agon
    -0.14
    Æ¡
    -0.14
     Fashion
    -0.14
     меÑĤалли
    -0.14
    ][_
    -0.14
    780
    -0.13
     ActionTypes
    -0.13
    POSITIVE LOGITS
    elf
    0.15
    ilter
    0.15
    erp
    0.14
    enance
    0.14
    eb
    0.14
    çºĮ
    0.14
    uer
    0.14
    ÑĪка
    0.14
    ekte
    0.13
     aks
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.