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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    inois
    -0.87
    berman
    -0.71
    ousand
    -0.69
    erella
    -0.67
    ruary
    -0.67
    atin
    -0.66
    aukee
    -0.66
    ricane
    -0.65
     Ago
    -0.65
    committee
    -0.64
    POSITIVE LOGITS
     Signs
    0.69
    spot
    0.65
     Sharks
    0.62
     Jungle
    0.61
     Krug
    0.61
     Newsp
    0.59
     cav
    0.59
     sign
    0.58
     pun
    0.57
     Cove
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.