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

    Neuronpedia

    INDEX
    Explanations

    phrases that express obligations or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iske
    -0.17
     Verde
    -0.16
    elage
    -0.16
    phia
    -0.15
    oras
    -0.15
    uge
    -0.14
    atron
    -0.14
     Spot
    -0.14
    grund
    -0.14
    uras
    -0.13
    POSITIVE LOGITS
    igham
    0.17
     Gim
    0.15
     Barrett
    0.14
     ashamed
    0.14
     BÃł
    0.13
    bai
    0.13
    ½æķ°
    0.13
    ercise
    0.13
    ãĥ¼ãĥ³
    0.13
    -title
    0.13
    Act Density 0.243%

    No Known Activations