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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctor
    -0.15
    orman
    -0.15
    ék
    -0.14
    iants
    -0.14
     Gates
    -0.14
    alendar
    -0.14
     Jacobs
    -0.13
    алÑĭ
    -0.13
     bast
    -0.13
    etc
    -0.13
    POSITIVE LOGITS
     is
    0.20
    -this
    0.18
    Whole
    0.16
     whole
    0.16
    âĢĮس
    0.15
    æĺ¯æĪij
    0.15
    _requires
    0.15
     morning
    0.15
     ones
    0.14
    ÏĪε
    0.14
    Act Density 0.114%

    No Known Activations