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

    Neuronpedia

    INDEX
    Explanations

    terms associated with organizational roles and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lisi
    -0.17
    oins
    -0.17
    rrha
    -0.15
    fak
    -0.15
    ayo
    -0.14
    krom
    -0.14
    PCP
    -0.14
    ibold
    -0.14
    DonaldTrump
    -0.13
    СÐŀ
    -0.13
    POSITIVE LOGITS
    418
    0.17
    vere
    0.16
     might
    0.15
     sore
    0.15
    695
    0.15
    658
    0.14
    uje
    0.14
     Umb
    0.14
     can
    0.14
    ane
    0.14
    Act Density 0.143%

    No Known Activations