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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝐢
    1.48
    ⨔
    1.38
    <unused1873>
    1.34
    <unused591>
    1.31
    <unused1145>
    1.30
    𝐚
    1.29
    ۰۰
    1.26
    <unused1037>
    1.26
    творення
    1.25
    Einstellungen
    1.24
    POSITIVE LOGITS
    lo
    1.37
    ot
    1.11
     lem
    1.10
    el
    1.07
    es
    1.04
    lose
    1.03
    le
    1.02
    ra
    1.00
    ort
    1.00
    mail
    0.99
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.