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

    Neuronpedia

    INDEX
    Explanations

    mentions of the English language and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickle
    -0.08
    ecom
    -0.07
    TER
    -0.07
    AGR
    -0.07
    atel
    -0.07
    finder
    -0.07
    omial
    -0.07
    rames
    -0.07
    ucu
    -0.06
    ycz
    -0.06
    POSITIVE LOGITS
    -speaking
    0.12
    -language
    0.11
    enment
    0.10
    men
    0.10
    man
    0.10
    woman
    0.09
    erman
    0.09
    ness
    0.09
    spe
    0.09
    women
    0.08
    Act Density 0.018%

    No Known Activations