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

    Neuronpedia

    INDEX
    Explanations

    words related to risk and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (Unknown
    -0.14
    phan
    -0.14
    cobra
    -0.14
    extras
    -0.14
    roys
    -0.14
    [last
    -0.14
    Untitled
    -0.14
    onya
    -0.14
    imet
    -0.13
    jsc
    -0.13
    POSITIVE LOGITS
     /
    0.22
     âģ
    0.16
    Collapse
    0.16
     Wu
    0.16
     Collapse
    0.15
     Left
    0.15
    ugen
    0.15
     /↵
    0.15
    .news
    0.14
     Bout
    0.14
    Act Density 0.001%

    No Known Activations