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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reasons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.62
    👈
    -0.57
     noget
    -0.52
    HandlerContext
    -0.50
    ån
    -0.48
    stalt
    -0.47
    ǒ
    -0.47
     linho
    -0.47
    屁
    -0.47
     okru
    -0.47
    POSITIVE LOGITS
     many
    0.67
     OFDb
    0.66
    principalTable
    0.64
    hermosa
    0.63
    UserScript
    0.61
     consultato
    0.59
    Portail
    0.59
    存于互联网档案馆
    0.58
    many
    0.58
    enumii
    0.57
    Act Density 0.872%

    No Known Activations