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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ,"
    1.10
     metaphor
    1.00
     coffee
    0.97
     chair
    0.96
    0.94
     >
    0.94
     gut
    0.94
     -->
    0.92
    ic
    0.92
     eternal
    0.91
    POSITIVE LOGITS
    enquête
    1.12
    ের
    1.07
     Rxb
    1.07
    ायतों
    1.03
    ଙ୍କ
    1.02
    handles
    1.00
    𝒇
    0.99
    sman
    0.99
    proficiency
    0.98
    倞
    0.97
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.