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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "addition" indicating supplemental information or further explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atten
    -0.16
    ivals
    -0.15
    گرÛĮ
    -0.14
    aju
    -0.14
    zenia
    -0.14
    apsed
    -0.14
    ë¹Ī
    -0.14
    åħĴ
    -0.13
    à¥įबर
    -0.13
    ãģªãĤĵ
    -0.13
    POSITIVE LOGITS
    tion
    0.27
    nal
    0.22
    ition
    0.20
    ally
    0.19
    phia
    0.18
    eel
    0.18
    iton
    0.16
    tal
    0.16
    ordinary
    0.16
    ormal
    0.16
    Act Density 0.020%

    No Known Activations