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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to the speaker or groups they belong to

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "I" and its variations, indicating a focus on personal experiences and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.82
    uffer
    -0.69
    Weak
    -0.62
    itutes
    -0.61
     impunity
    -0.60
    âĶģ
    -0.60
     curfew
    -0.60
    flush
    -0.59
     Toggle
    -0.58
    capacity
    -0.57
    POSITIVE LOGITS
     realized
    1.38
     realised
    1.28
     searched
    1.26
     stumbled
    1.25
     noticed
    1.24
     discovered
    1.23
     contacted
    1.22
     proceeded
    1.20
     figured
    1.19
     consulted
    1.18
    Act Density 0.418%

    No Known Activations