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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive attributes or affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oplan
    -0.17
    uggy
    -0.15
     sez
    -0.14
    pei
    -0.14
    anch
    -0.14
     subtitle
    -0.14
     anchor
    -0.14
    elop
    -0.14
    uye
    -0.13
    ropolitan
    -0.13
    POSITIVE LOGITS
     virtually
    0.16
    hol
    0.16
    LEGRO
    0.15
     skoro
    0.15
     Physical
    0.15
     almost
    0.15
     nearly
    0.15
    oric
    0.15
    esteem
    0.15
    ĵåIJį
    0.15
    Act Density 0.021%

    No Known Activations