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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dismant
    -0.98
    ablishment
    -0.88
    ambers
    -0.79
    obin
    -0.72
    acebook
    -0.71
    arantine
    -0.70
    ulla
    -0.70
    opes
    -0.69
    atan
    -0.68
    apters
    -0.67
    POSITIVE LOGITS
    natureconservancy
    0.80
     quad
    0.75
     keynote
    0.72
     Featured
    0.65
    conference
    0.65
     Leap
    0.64
    CCC
    0.64
    0.63
     Purple
    0.63
    star
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.