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

    Neuronpedia

    INDEX
    Explanations

    organizations and locations, especially names of institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to government or institutional entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.65
    Sov
    -0.62
     agre
    -0.58
    because
    -0.58
    ãģĦ
    -0.58
    bes
    -0.58
    every
    -0.57
     slic
    -0.56
    Ò
    -0.56
    zers
    -0.56
    POSITIVE LOGITS
     âĵĺ
    1.01
     ·
    0.82
     âĢº
    0.82
     |
    0.76
     -----
    0.73
     welcomes
    0.72
     Announce
    0.70
     Originally
    0.68
     Website
    0.67
     Latest
    0.67
    Act Density 0.482%

    No Known Activations