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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atility
    -0.74
    ointed
    -0.72
    catentry
    -0.71
     indirect
    -0.65
     manoeuv
    -0.64
    edIn
    -0.64
    ttes
    -0.63
    erala
    -0.61
    laus
    -0.61
     ACTIONS
    -0.61
    POSITIVE LOGITS
     Proud
    0.66
    oa
    0.65
     alphabet
    0.62
    !--
    0.61
    found
    0.60
     Blaze
    0.60
     blush
    0.59
    bill
    0.58
    jad
    0.58
     ben
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.