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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     listener
    -0.73
     affili
    -0.72
     disemb
    -0.72
     pit
    -0.68
    icent
    -0.68
     brief
    -0.67
    isl
    -0.65
     barg
    -0.64
     bre
    -0.64
     tyr
    -0.64
    POSITIVE LOGITS
     Moreover
    1.33
     Hence
    1.28
     Consequently
    1.25
     Therefore
    1.22
     Thus
    1.21
     Furthermore
    1.15
     Indeed
    1.14
     So
    1.14
     Specifically
    1.13
     Notably
    1.11
    Act Density 0.619%

    No Known Activations