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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation symbols

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jordanian
    -0.80
     squats
    -0.67
     Kass
    -0.64
     interns
    -0.64
     Ghana
    -0.62
     facilit
    -0.62
     Casey
    -0.62
     camps
    -0.62
     persuasion
    -0.62
     Kat
    -0.61
    POSITIVE LOGITS
    \
    2.25
    }\
    2.16
    _{
    1.91
    "}
    1.90
    \"
    1.88
    }}
    1.87
    {\
    1.81
    \)
    1.78
    ^{
    1.77
    )\
    1.74
    Act Density 0.031%

    No Known Activations