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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    raltar
    -0.79
    abouts
    -0.78
    arant
    -0.74
    adal
    -0.73
    station
    -0.73
    mor
    -0.73
    noon
    -0.72
    thur
    -0.72
    ãĥ´ãĤ¡
    -0.72
    dor
    -0.71
    POSITIVE LOGITS
     playbook
    0.80
     Masquerade
    0.71
     quotes
    0.70
     phony
    0.66
     impression
    0.64
     ratio
    0.63
     bathroom
    0.63
     script
    0.62
     cumbers
    0.62
     threads
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.