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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.15
     sometimes
    -0.14
     opak
    -0.14
    sometimes
    -0.14
    æĤ¨
    -0.14
    µľ
    -0.13
    ascript
    -0.13
    uebas
    -0.13
    iom
    -0.13
    oki
    -0.13
    POSITIVE LOGITS
     likely
    0.24
     unless
    0.24
     will
    0.23
     whether
    0.23
     Whether
    0.22
     expect
    0.22
     upcoming
    0.21
    unless
    0.21
     Unless
    0.20
    Whether
    0.20
    Act Density 0.382%

    No Known Activations