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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names, titles, and roles related to individuals in a political or official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coma
    -0.55
     Lithuan
    -0.55
     cav
    -0.53
     amphib
    -0.53
    ĪĴ
    -0.53
    ï¸
    -0.51
     decom
    -0.51
    tsky
    -0.51
     Georgian
    -0.50
    çķ
    -0.50
    POSITIVE LOGITS
    office
    0.78
    ciation
    0.63
    ORTS
    0.62
    ordan
    0.60
    dq
    0.59
    issance
    0.57
    approved
    0.57
    incial
    0.55
    autions
    0.54
    ruary
    0.54
    Act Density 1.142%

    No Known Activations