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

    Neuronpedia

    INDEX
    Explanations

    numerical values and expressions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.16
    aso
    -0.15
     thumbs
    -0.15
     Shapiro
    -0.15
    usz
    -0.14
    lum
    -0.14
    esium
    -0.14
    inski
    -0.14
    mart
    -0.13
    assic
    -0.13
    POSITIVE LOGITS
    à¹Ģà¸ķà¸Ńร
    0.15
    EXPR
    0.15
     etc
    0.15
    μιÏĥ
    0.14
    Slf
    0.14
    ãģķãĤī
    0.14
    çĽĬ
    0.14
    廳
    0.14
    룸
    0.13
    anda
    0.13
    Act Density 0.049%

    No Known Activations