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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms related to individuals, particularly political figures or leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yo
    -0.19
    tainment
    -0.15
     Lair
    -0.15
    ла
    -0.15
     Yates
    -0.14
    obox
    -0.14
    ourcem
    -0.14
    ExecutionContext
    -0.14
    айÑĤ
    -0.14
    ¯
    -0.14
    POSITIVE LOGITS
    ût
    0.23
    erg
    0.18
    osy
    0.16
    irse
    0.15
    BAB
    0.15
    xygen
    0.15
    Insensitive
    0.15
    оÑģÑĮ
    0.15
    anan
    0.14
    chy
    0.14
    Act Density 0.022%

    No Known Activations