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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity and diversity across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emode
    -0.14
    ebi
    -0.14
    ular
    -0.14
    ucht
    -0.14
     alternatives
    -0.14
     semiclass
    -0.14
    ован
    -0.13
    ffen
    -0.13
     Date
    -0.13
    keh
    -0.13
    POSITIVE LOGITS
     backgrounds
    0.38
     walks
    0.37
    background
    0.33
     Background
    0.32
     background
    0.32
     ages
    0.31
     persu
    0.27
    walk
    0.27
     races
    0.27
    Background
    0.26
    Act Density 0.061%

    No Known Activations