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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    utsche
    -0.89
    nih
    -0.81
    lehem
    -0.75
    otle
    -0.75
    dain
    -0.75
    ghazi
    -0.75
    odon
    -0.74
    */(
    -0.74
    tein
    -0.73
    zbollah
    -0.73
    POSITIVE LOGITS
     Minor
    0.69
     Tactics
    0.66
    arger
    0.63
     Spaces
    0.62
    quist
    0.61
     Ross
    0.61
     Compact
    0.61
    PAC
    0.60
     Goddess
    0.58
     Prim
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.