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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äºĮäºĮ
    -0.15
    stad
    -0.15
    rieve
    -0.15
    olulu
    -0.14
    ideographic
    -0.14
    ../
    -0.14
    ког
    -0.14
    laus
    -0.14
    à¹ĥà¸Ī
    -0.14
    lus
    -0.14
    POSITIVE LOGITS
    nd
    0.32
    -thirds
    0.26
    ï¸ı
    0.22
     dozen
    0.20
    gether
    0.19
    nder
    0.19
    ième
    0.16
     thirds
    0.16
    ehir
    0.16
    /th
    0.16
    Act Density 0.572%

    No Known Activations