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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection and usage for analysis or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¦
    -0.07
    oningen
    -0.07
    æĵ
    -0.07
    iversal
    -0.07
    umm
    -0.07
    TestingModule
    -0.07
    vana
    -0.06
    odynam
    -0.06
    fois
    -0.06
    orsche
    -0.06
    POSITIVE LOGITS
    UTE
    0.06
    563
    0.06
     measures
    0.06
    282
    0.06
    enido
    0.05
     suite
    0.05
    dad
    0.05
    ADB
    0.05
    elry
    0.05
     inspiration
    0.05
    Act Density 0.002%

    No Known Activations