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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to falsehoods and misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialized
    -0.16
    ikk
    -0.16
    lesi
    -0.15
    Bias
    -0.14
    igel
    -0.14
    adiens
    -0.14
    igs
    -0.14
    íĻ©
    -0.14
    tones
    -0.14
    ุà¸ķ
    -0.14
    POSITIVE LOGITS
    /false
    0.16
    ocrat
    0.16
     claim
    0.16
     premises
    0.15
    .localized
    0.14
    aina
    0.14
    HD
    0.14
    ktop
    0.14
     claims
    0.14
    омеÑĢ
    0.14
    Act Density 0.089%

    No Known Activations