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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.71
     Dos
    -0.68
    --------
    -0.67
    HF
    -0.66
     Seth
    -0.65
     Lions
    -0.64
    ================
    -0.62
     NK
    -0.61
     Integrity
    -0.61
    Sat
    -0.61
    POSITIVE LOGITS
    ipeg
    0.74
    iddler
    0.73
    aves
    0.72
    oped
    0.72
    bda
    0.71
    sburgh
    0.71
    rano
    0.70
    sson
    0.70
    luent
    0.68
    upon
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.