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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hoodies
    0.42
     pouches
    0.42
     epistemology
    0.41
     layouts
    0.40
     chestnuts
    0.39
    🖇
    0.38
     pantai
    0.38
    🦑
    0.38
     weiter
    0.38
    wość
    0.38
    POSITIVE LOGITS
    sta
    0.31
    ge
    0.30
    it
    0.30
    lar
    0.30
    Type
    0.29
    ones
    0.29
    sm
    0.29
    {{
    0.28
    star
    0.27
    in
    0.27
    Act Density 0.671%

    No Known Activations