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

    Neuronpedia

    INDEX
    Explanations

    phrases that express requests or appeals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç§
    -0.17
    ãĥ¼ãĥĢ
    -0.15
    heck
    -0.14
    Ñħа
    -0.14
    engl
    -0.14
    aben
    -0.14
    éŀ
    -0.14
    iks
    -0.14
    iyon
    -0.13
    оваÑĢи
    -0.13
    POSITIVE LOGITS
    ayar
    0.15
    inous
    0.15
     ruce
    0.15
    pend
    0.15
    ined
    0.14
    BuilderInterface
    0.14
    entr
    0.14
    ille
    0.14
    lix
    0.14
    ged
    0.14
    Act Density 0.122%

    No Known Activations