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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -->
    -0.71
    olo
    -0.68
     appliance
    -0.66
     Entered
    -0.60
    ching
    -0.60
    oming
    -0.57
     slowed
    -0.57
     productivity
    -0.56
    )=
    -0.56
     (~
    -0.56
    POSITIVE LOGITS
    ©¶æ¥µ
    0.81
    urai
    0.77
    ãĤ¨ãĥ«
    0.72
    Fair
    0.67
    Ĥİ
    0.67
     Dia
    0.66
     Rept
    0.64
    estine
    0.64
     Flood
    0.63
    adh
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.