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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥĥãĥĪ
    -0.17
    åŀĤ
    -0.17
     radial
    -0.15
     Fant
    -0.15
    lob
    -0.14
    ttp
    -0.14
    اÙĨت
    -0.14
    ureau
    -0.14
    olic
    -0.13
    sett
    -0.13
    POSITIVE LOGITS
    nds
    0.17
    лини
    0.16
    eus
    0.15
    ispers
    0.15
    hape
    0.15
     lit
    0.14
    иÑģк
    0.14
    airo
    0.14
    ÄĻk
    0.14
    etheus
    0.14
    Act Density 0.029%

    No Known Activations