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

    Neuronpedia

    INDEX
    Explanations

    statements of knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.77
    CELLANEOUS
    -0.72
    namental
    -0.67
     myſelf
    -0.64
    AnchorStyles
    -0.62
    luo
    -0.62
    rungsseite
    -0.61
    dinga
    -0.61
    plevel
    -0.60
    essment
    -0.58
    POSITIVE LOGITS
     known
    0.91
     know
    0.80
     Known
    0.80
    Known
    0.79
     diketahui
    0.77
     knows
    0.77
     KNOWN
    0.76
     sabemos
    0.75
    known
    0.70
     知道
    0.64
    Act Density 0.339%

    No Known Activations