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

    Neuronpedia

    INDEX
    Explanations

    references to the pronoun "it" and contextually related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    it is or the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.38
     acompañada
    -0.35
     Мексичка
    -0.35
    RetentionPolicy
    -0.34
     šķ
    -0.33
     acompañado
    -0.33
    ArrowToggle
    -0.30
     Italijani
    -0.29
    Referanser
    -0.28
    лтамалар
    -0.28
    POSITIVE LOGITS
     パンチラ
    0.81
    [@BOS@]
    0.79
    <unused47>
    0.79
    <unused79>
    0.79
    <unused28>
    0.78
    <unused14>
    0.78
    <unused23>
    0.78
    <unused41>
    0.78
    <unused8>
    0.78
    <pad>
    0.78
    Act Density 0.180%

    No Known Activations