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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and variations of "that" in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullo
    -0.18
    anny
    -0.15
    vr
    -0.14
    ücken
    -0.14
    ixel
    -0.14
    rv
    -0.14
    matter
    -0.14
    наÑĤ
    -0.14
    kaar
    -0.14
    лаÑĪ
    -0.14
    POSITIVE LOGITS
    å½ĵçĦ¶
    0.15
    天åłĤ
    0.14
     fact
    0.14
    eyim
    0.14
    IFS
    0.14
    perience
    0.14
    ãĥ³ãĤ¸
    0.14
    positories
    0.14
    à¹Ģà¸Ńà¸ĩ
    0.14
     experience
    0.14
    Act Density 0.096%

    No Known Activations