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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases centered around relationships and emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WE
    -0.15
    itra
    -0.15
     Hang
    -0.14
    iden
    -0.14
    itr
    -0.14
    ORIZED
    -0.14
    raquo
    -0.14
    cheiden
    -0.14
     çĶŁåij½åij¨æľŁåĩ½æķ°
    -0.14
    ä½ı
    -0.14
    POSITIVE LOGITS
    ohon
    0.15
     intentions
    0.15
     vel
    0.15
     intention
    0.14
    éal
    0.14
     Baths
    0.14
    евÑĸ
    0.14
    è§īå¾Ĺ
    0.14
     Maar
    0.14
    raci
    0.14
    Act Density 0.135%

    No Known Activations