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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ⏶
    -0.07
     miłości
    -0.07
    	dist
    -0.07
     pais
    -0.07
    lane
    -0.07
     mel
    -0.06
    imes
    -0.06
     instr
    -0.06
     המכ
    -0.06
    $page
    -0.06
    POSITIVE LOGITS
    -funded
    0.07
    𬭚
    0.07
    😡
    0.07
     volatile
    0.07
     fireworks
    0.07
    油烟
    0.07
     priceless
    0.07
    SplitOptions
    0.06
    _depth
    0.06
     nächsten
    0.06
    Act Density 0.027%

    No Known Activations