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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    })
    -0.77
    Reply
    -0.73
     Despair
    -0.67
    >)
    -0.66
    ellery
    -0.66
     ])
    -0.64
     ItemLevel
    -0.63
    reetings
    -0.62
     purse
    -0.62
     ))
    -0.62
    POSITIVE LOGITS
    forces
    0.71
    ãĥĦ
    0.70
    XM
    0.69
    fm
    0.67
    aur
    0.66
    FML
    0.64
    imer
    0.64
     lucid
    0.63
     Afgh
    0.62
     Ages
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.