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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote inclusion or offering various options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mt
    -0.17
    adol
    -0.16
    illes
    -0.15
    ove
    -0.15
    ubb
    -0.15
     spanking
    -0.14
    entic
    -0.14
     promotion
    -0.14
    prom
    -0.14
    aste
    -0.14
    POSITIVE LOGITS
    eltas
    0.17
     Bylo
    0.16
    åį
    0.16
    uran
    0.15
     Porno
    0.15
    åľĴ
    0.15
    ÅĤaw
    0.15
    gün
    0.14
    elocity
    0.14
    ReuseIdentifier
    0.14
    Act Density 0.226%

    No Known Activations