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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sheets
    -0.77
     cob
    -0.71
    SIGN
    -0.69
    "},"
    -0.64
    Translation
    -0.62
    Documents
    -0.61
    heid
    -0.61
    ecause
    -0.61
    Minecraft
    -0.61
     quotas
    -0.60
    POSITIVE LOGITS
     wearer
    0.74
    icrobial
    0.73
    eness
    0.72
     Savage
    0.68
    etts
    0.68
    antha
    0.64
     utility
    0.64
    gres
    0.63
    ifact
    0.62
    ett
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.