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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     heter
    -0.07
     Jets
    -0.07
    から
    -0.06
    {!!
    -0.06
    (blank
    -0.06
    ={()=>
    -0.06
    .answers
    -0.06
    (recv
    -0.06
     agenda
    -0.06
    chez
    -0.06
    POSITIVE LOGITS
    timeofday
    0.07
    Erreur
    0.07
    PTY
    0.07
    엾
    0.07
    _SUP
    0.07
    мат
    0.07
     sailing
    0.07
    rical
    0.07
     Sar
    0.07
    .Modules
    0.07
    Act Density 0.128%

    No Known Activations