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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     better
    -0.08
     descendant
    -0.07
    琪
    -0.07
     Gratis
    -0.07
     detect
    -0.07
     Pearce
    -0.06
     place
    -0.06
     poco
    -0.06
     Perr
    -0.06
    ない
    -0.06
    POSITIVE LOGITS
    TRANS
    0.07
    .MODEL
    0.07
    �
    0.07
    olesale
    0.06
    מרכ
    0.06
    早晚
    0.06
    (strings
    0.06
    فناد
    0.06
    RAND
    0.06
     HAL
    0.06
    Act Density 0.034%

    No Known Activations