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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political matters and discourses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    479
    -0.13
    ogl
    -0.13
    awan
    -0.13
    £p
    -0.13
    Assert
    -0.13
    enso
    -0.13
    Ñĩа
    -0.13
    Æ°á»Ŀng
    -0.13
    asta
    -0.13
    elog
    -0.13
    POSITIVE LOGITS
     objective
    0.57
     neutral
    0.54
     impartial
    0.51
     unbiased
    0.48
     neutrality
    0.47
    objective
    0.46
     Neutral
    0.45
    -neutral
    0.45
    neutral
    0.45
    Neutral
    0.44
    Act Density 0.360%

    No Known Activations