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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingleton
    -0.16
    iye
    -0.15
    ugh
    -0.15
     wet
    -0.14
    stk
    -0.14
    wr
    -0.14
    igli
    -0.14
    íĤ¬
    -0.13
    akah
    -0.13
     wykon
    -0.13
    POSITIVE LOGITS
    CMS
    0.15
    heim
    0.15
    tern
    0.15
    SCRI
    0.14
    пÑĢав
    0.14
    lotte
    0.14
    ãģ¾ãģ¾
    0.14
    IRST
    0.14
    ifornia
    0.14
    ERN
    0.14
    Act Density 0.054%

    No Known Activations