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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "similar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rip
    -0.19
    ype
    -0.15
    urdy
    -0.15
     Erect
    -0.14
    vla
    -0.14
    hos
    -0.14
    ses
    -0.14
     Tyler
    -0.14
     नà¤ķ
    -0.14
    upil
    -0.14
    POSITIVE LOGITS
    apore
    0.17
    ily
    0.16
    -sex
    0.15
     ilk
    0.15
     eldre
    0.15
    -minded
    0.15
     minded
    0.14
    Fixture
    0.14
    arhus
    0.14
     gest
    0.14
    Act Density 0.018%

    No Known Activations