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

    Neuronpedia

    INDEX
    Explanations

    quantities related to individuals and their experiences or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucid
    -0.17
     нада
    -0.16
    ItemCount
    -0.15
    ÙĨاÙĨ
    -0.15
    }}],↵
    -0.15
    agi
    -0.14
    uze
    -0.14
    oleans
    -0.14
    RIORITY
    -0.14
    æĪIJç«ĭ
    -0.14
    POSITIVE LOGITS
     contrast
    0.17
    ¹Ħ
    0.17
     unlike
    0.16
    ander
    0.16
     access
    0.15
     Vs
    0.15
     vs
    0.15
     promised
    0.15
     versus
    0.15
     vows
    0.15
    Act Density 0.003%

    No Known Activations