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

    Neuronpedia

    INDEX
    Explanations

    terms related to stipulations and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aping
    -0.15
    çĶº
    -0.15
    otate
    -0.15
    tres
    -0.15
    hound
    -0.14
     èij
    -0.14
    lier
    -0.14
    鹿
    -0.14
    Łèĥ½
    -0.14
    lek
    -0.14
    POSITIVE LOGITS
    ulation
    0.19
    ulus
    0.19
    endi
    0.18
    pled
    0.18
    ple
    0.18
    ulated
    0.15
    ulate
    0.15
    uard
    0.15
    phia
    0.15
    ulative
    0.15
    Act Density 0.007%

    No Known Activations