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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ó
    -0.80
    ussion
    -0.76
    opian
    -0.73
     paycheck
    -0.69
     Parenthood
    -0.67
    WN
    -0.67
    ccording
    -0.66
    PF
    -0.65
    aples
    -0.65
     Sof
    -0.65
    POSITIVE LOGITS
    arger
    0.65
     boots
    0.64
     roofs
    0.63
     thirds
    0.63
    ãĥİ
    0.63
     subdiv
    0.62
     boats
    0.61
    empty
    0.60
     exception
    0.60
    ashes
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.