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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promoting progress or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -0.14
     Violence
    -0.13
    ilded
    -0.13
    ucks
    -0.13
     jo
    -0.13
    cats
    -0.13
    namen
    -0.13
    CID
    -0.13
    ners
    -0.12
    106
    -0.12
    POSITIVE LOGITS
     incent
    0.15
    illes
    0.15
    ANCED
    0.15
    OwnProperty
    0.15
     advancement
    0.14
    INCLUDED
    0.14
    illary
    0.14
     taper
    0.14
     Aires
    0.14
    CELER
    0.14
    Act Density 0.020%

    No Known Activations