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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.74
     Streets
    -0.69
    fif
    -0.67
    mbuds
    -0.66
     Explain
    -0.65
     Debate
    -0.64
    obyl
    -0.63
     Legions
    -0.61
    escape
    -0.61
     Revenge
    -0.61
    POSITIVE LOGITS
    rament
    0.73
    alty
    0.71
    ORED
    0.70
    ukong
    0.67
    auga
    0.67
    ensor
    0.67
    Param
    0.66
    iencies
    0.64
    Calif
    0.62
    OOL
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.