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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political endorsements and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPA
    -0.16
    382
    -0.15
    owski
    -0.15
    odia
    -0.15
    476
    -0.14
    à¸Ĺาà¸ĩ
    -0.14
    cth
    -0.14
    bens
    -0.14
    Enlarge
    -0.13
    pell
    -0.13
    POSITIVE LOGITS
    iant
    0.17
    ient
    0.16
    ÑĪел
    0.15
     Hood
    0.15
    ients
    0.14
    noxious
    0.14
    nar
    0.14
    udy
    0.14
     fora
    0.13
     poisoned
    0.13
    Act Density 0.005%

    No Known Activations