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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    alach
    -0.73
    Ü
    -0.70
     fal
    -0.67
     sleeper
    -0.66
    icators
    -0.66
    rehens
    -0.65
    iations
    -0.64
    utherland
    -0.64
    iated
    -0.61
    ablished
    -0.61
    POSITIVE LOGITS
    SPONSORED
    0.85
    bard
    0.79
    HD
    0.76
    Else
    0.75
    mary
    0.74
     MAD
    0.66
    ONY
    0.65
    AMY
    0.65
    uncle
    0.65
    HAM
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.