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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tyr
    -0.65
    UGH
    -0.65
     Inventory
    -0.62
    Emily
    -0.61
    Cra
    -0.61
     Dayton
    -0.60
     licking
    -0.59
    course
    -0.59
     Eleven
    -0.58
    Priv
    -0.57
    POSITIVE LOGITS
     involves
    1.26
     coincided
    1.16
     coincides
    1.16
     relates
    1.16
     contradicts
    1.15
     represents
    1.15
     contains
    1.12
     violates
    1.06
     promotes
    1.03
     removes
    1.03
    Act Density 0.132%

    No Known Activations