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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.79
     Parables
    -0.78
     Consortium
    -0.76
     è£ıè
    -0.70
    ĵĺ
    -0.68
    ãĤ¤ãĥĪ
    -0.68
    igmatic
    -0.67
     Enhance
    -0.65
    ãĤ´ãĥ³
    -0.65
    Indeed
    -0.64
    POSITIVE LOGITS
     got
    1.35
     didn
    1.35
     went
    1.33
     didnt
    1.32
     stayed
    1.27
     threw
    1.27
     blew
    1.25
     messed
    1.23
     forgot
    1.22
     kept
    1.21
    Act Density 0.330%

    No Known Activations