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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases indicating similarity or sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekim
    -0.16
    sein
    -0.15
    969
    -0.15
    rious
    -0.15
    ses
    -0.15
    pri
    -0.14
    pk
    -0.14
    printStats
    -0.14
    licht
    -0.14
    onom
    -0.14
    POSITIVE LOGITS
    -sex
    0.24
     kind
    0.18
    -sama
    0.18
     sort
    0.16
    ãĤĪãģĨãģª
    0.16
     thing
    0.16
    -old
    0.16
    èĥŀ
    0.16
    iro
    0.16
    ily
    0.15
    Act Density 0.057%

    No Known Activations