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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve questions and statements addressing "you" and "we."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sortable
    -0.15
    ecided
    -0.15
    ulis
    -0.15
     surprises
    -0.14
    orgen
    -0.14
    igua
    -0.14
    лава
    -0.13
    elerik
    -0.13
    avia
    -0.13
    iÄħ
    -0.13
    POSITIVE LOGITS
     look
    0.29
    look
    0.26
     looked
    0.23
    .look
    0.23
     zoom
    0.22
     looks
    0.22
     LOOK
    0.22
     compare
    0.22
     Google
    0.21
     factor
    0.21
    Act Density 0.099%

    No Known Activations