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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ordial
    -0.74
    eties
    -0.73
    iate
    -0.73
     renegoti
    -0.72
    aghan
    -0.71
    ym
    -0.71
    qua
    -0.68
    acho
    -0.68
    ounce
    -0.67
     veto
    -0.66
    POSITIVE LOGITS
    ]=
    0.82
    IDES
    0.81
    ]+
    0.80
     partName
    0.77
     dstg
    0.75
    GROUND
    0.74
     Stafford
    0.73
    TEXT
    0.72
    Notice
    0.72
    DES
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.