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

    Neuronpedia

    INDEX
    Explanations

    details related to politics and international relations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliated
    -0.64
    omi
    -0.62
     affected
    -0.61
     aided
    -0.61
    tarian
    -0.60
    gur
    -0.60
    ollen
    -0.59
    IUM
    -0.58
    ifax
    -0.57
     supplemented
    -0.57
    POSITIVE LOGITS
    itiveness
    0.80
     Mouth
    0.70
    center
    0.65
     heels
    0.63
    oeuv
    0.62
    eat
    0.62
     Caesar
    0.62
     mole
    0.61
    bows
    0.60
     Rails
    0.60
    Act Density 3.024%

    No Known Activations