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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.21
     known
    -0.21
     know
    -0.20
     Known
    -0.18
     Indeed
    -0.18
    Known
    -0.17
    inde
    -0.17
     knows
    -0.17
     knew
    -0.17
    Indeed
    -0.17
    POSITIVE LOGITS
     like
    0.16
    лÑİÑĩа
    0.16
     sometimes
    0.15
    Sort
    0.15
     jus
    0.15
    ruba
    0.15
    just
    0.15
     Sometimes
    0.14
    when
    0.14
    èĪ¬
    0.14
    Act Density 0.019%

    No Known Activations