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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pees
    -0.77
    abet
    -0.77
    Reader
    -0.72
    reads
    -0.68
    ttp
    -0.68
    pite
    -0.67
    raq
    -0.66
    oub
    -0.64
    arbon
    -0.64
    secut
    -0.63
    POSITIVE LOGITS
     quarantine
    0.71
     Mandatory
    0.62
     steroid
    0.62
     contingent
    0.61
     harbor
    0.61
     penalties
    0.60
     Abyssal
    0.59
     mercury
    0.59
    chuk
    0.59
     Photographer
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.