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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ovie
    -0.84
    QB
    -0.83
    vernment
    -0.78
    endi
    -0.76
    çĭ
    -0.70
    KR
    -0.67
    elong
    -0.67
    Ïī
    -0.66
    lynn
    -0.66
    fre
    -0.66
    POSITIVE LOGITS
     Hide
    0.76
     Philos
    0.76
     Armor
    0.74
     illum
    0.71
     Forbidden
    0.71
    cius
    0.68
     shroud
    0.67
    iologist
    0.65
     mats
    0.64
    mite
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.