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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names associated with legal cases and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.82
    enumi
    -0.78
    twimg
    -0.77
     &___
    -0.73
    parsedMessage
    -0.72
    ]--;
    -0.71
     Schme
    -0.69
    EndInit
    -0.69
     Heff
    -0.68
    IFORNIA
    -0.68
    POSITIVE LOGITS
    ,
    0.53
     abbraccio
    0.51
    omalainen
    0.47
     Brothers
    0.43
     Brown
    0.43
     Jr
    0.43
     et
    0.41
    慢
    0.41
    gráfica
    0.40
    หนัง
    0.40
    Act Density 0.745%

    No Known Activations