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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     endeavour
    -0.17
     humour
    -0.17
     instantiation
    -0.16
     coloured
    -0.16
     favour
    -0.15
     neighbouring
    -0.15
     favourable
    -0.15
     judgement
    -0.15
     iter
    -0.15
     programme
    -0.15
    POSITIVE LOGITS
     Frankie
    0.30
     Franklin
    0.16
    Frank
    0.15
     Joey
    0.15
     Richie
    0.15
    اÙĪÙĬ
    0.15
     frank
    0.15
     Neil
    0.15
     Frank
    0.14
     Lesb
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.