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

    Neuronpedia

    INDEX
    Explanations

    references to vulnerability and at-risk groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quil
    -0.15
    -gnu
    -0.15
    adata
    -0.15
    ilion
    -0.14
     Spi
    -0.14
    ueling
    -0.14
     bgcolor
    -0.13
    embros
    -0.13
    cede
    -0.13
    uslim
    -0.13
    POSITIVE LOGITS
    paper
    0.16
     Vulner
    0.15
    heart
    0.15
     frag
    0.15
    ies
    0.14
    اÙĪت
    0.14
    reck
    0.14
    kel
    0.14
    iver
    0.14
    keley
    0.14
    Act Density 0.014%

    No Known Activations