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

    Neuronpedia

    INDEX
    Explanations

    words that suggest uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.16
    isko
    -0.15
    atore
    -0.15
    elight
    -0.15
    estone
    -0.15
    eric
    -0.15
    idos
    -0.14
    ÑĢек
    -0.14
    eden
    -0.14
     MyBase
    -0.13
    POSITIVE LOGITS
    ibel
    0.15
    æķ
    0.14
    rahim
    0.14
    mrt
    0.14
    ((↵
    0.14
    é¸
    0.13
    engkap
    0.13
    ropic
    0.13
    morgan
    0.13
    移
    0.13
    Act Density 0.017%

    No Known Activations