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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases indicating exceptions or contrasting conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Numerade
    -0.47
     besonder
    -0.43
    حوالہ
    -0.42
     brows
    -0.42
     RECOM
    -0.40
     Bekasi
    -0.40
    Française
    -0.40
    篤
    -0.40
    啪
    -0.39
     yyhl
    -0.38
    POSITIVE LOGITS
     Malgré
    0.50
    尽管
    0.50
     Meskipun
    0.47
    Despite
    0.45
    Though
    0.45
     Despite
    0.45
    Meskipun
    0.44
    虽
    0.43
    Although
    0.43
    ostante
    0.43
    Act Density 0.545%

    No Known Activations