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

    Neuronpedia

    INDEX
    Explanations

    words that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.17
    ois
    -0.16
    ozor
    -0.15
    ocard
    -0.15
    rien
    -0.15
    ayah
    -0.15
    eç
    -0.14
    urai
    -0.14
    urd
    -0.14
    izzo
    -0.14
    POSITIVE LOGITS
    illon
    0.18
    razier
    0.17
    lum
    0.16
    _rl
    0.15
    ieu
    0.15
    ãĥ¼ãĥĦ
    0.14
    cum
    0.14
     bronze
    0.14
    agen
    0.14
    atu
    0.14
    Act Density 0.140%

    No Known Activations