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

    Neuronpedia

    INDEX
    Explanations

    descriptions of scenes or events involving people walking or sitting in various locations

    oai_token-act-pair · gpt-3.5-turbo

    components of descriptions involving people and their actions in various settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fact
    -0.88
    catentry
    -0.70
    enson
    -0.70
     ounce
    -0.69
     factor
    -0.68
     Secondly
    -0.67
    ãĥij
    -0.66
     accordingly
    -0.66
     Flavoring
    -0.65
    Secondly
    -0.64
    POSITIVE LOGITS
     silhou
    0.93
     surrounded
    0.92
     perched
    0.89
     sunset
    0.88
     sunrise
    0.84
     flanked
    0.83
     portrait
    0.82
    tyard
    0.81
    lication
    0.80
     boarded
    0.80
    Act Density 1.121%

    No Known Activations