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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    çĦ¶
    -0.18
    бÑĥд
    -0.17
    rael
    -0.17
    arf
    -0.16
    nard
    -0.16
    ari
    -0.15
    inese
    -0.14
    ARI
    -0.14
    lac
    -0.14
    burg
    -0.14
    POSITIVE LOGITS
    ul
    0.18
    've
    0.15
    ulp
    0.15
     if
    0.15
    ’ve
    0.14
    athers
    0.14
    istol
    0.14
     kdyby
    0.14
    ani
    0.14
    ANI
    0.14
    Act Density 0.532%

    No Known Activations