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

    Neuronpedia

    INDEX
    Explanations

    conversational affirmations and expressions of uncertainty or encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.15
     however
    -0.15
    mdp
    -0.15
    ARSER
    -0.15
    ži
    -0.15
    allee
    -0.14
    alon
    -0.14
     duro
    -0.14
    ether
    -0.14
    aken
    -0.14
    POSITIVE LOGITS
    ombok
    0.17
    ÙĪÙĨÛĮ
    0.14
    occo
    0.14
     Budd
    0.14
    วà¸Ļ
    0.14
    tail
    0.14
    .ls
    0.14
    κά
    0.14
    yps
    0.13
    ãĤ¿ãĥ¼
    0.13
    Act Density 0.451%

    No Known Activations