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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more" and related comparative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ado
    -0.14
    ardy
    -0.14
    ardo
    -0.13
    ÑĨо
    -0.13
    esser
    -0.13
    chg
    -0.13
    ard
    -0.13
    ازد
    -0.12
    anh
    -0.12
    à¥ĩà¤
    -0.12
    POSITIVE LOGITS
    umat
    0.14
    679
    0.13
    :both
    0.13
    zing
    0.13
    :UITableView
    0.13
    .rdf
    0.13
    gether
    0.13
    gle
    0.13
    /down
    0.13
     Îķν
    0.12
    Act Density 0.228%

    No Known Activations