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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nodd
    -0.89
    luaj
    -0.79
    quit
    -0.77
     describ
    -0.75
    etheless
    -0.75
    bul
    -0.74
    bestos
    -0.73
    mph
    -0.72
    ãĤ¨ãĥ«
    -0.71
    ItemImage
    -0.71
    POSITIVE LOGITS
    aneers
    0.75
    aters
    0.69
     Targ
    0.66
     Catalyst
    0.65
    ITION
    0.65
    ition
    0.64
    rell
    0.64
    ater
    0.63
    ASE
    0.63
     Tennessee
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.