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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social commentary and rhetoric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     revis
    -0.21
     salv
    -0.18
    tlement
    -0.17
    igation
    -0.16
    ÑħÑĸд
    -0.16
    ideographic
    -0.16
    elic
    -0.15
    ÙĪÛĮÛĮ
    -0.15
    enders
    -0.15
    ules
    -0.15
    POSITIVE LOGITS
    ize
    0.29
    ify
    0.28
    inize
    0.24
    itize
    0.23
    ise
    0.23
    inate
    0.22
    elize
    0.22
    isify
    0.21
    minate
    0.21
    iliate
    0.21
    Act Density 0.239%

    No Known Activations