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

    Neuronpedia

    INDEX
    Explanations

    software version numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical version indicators or updates related to software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.82
     deliber
    -0.77
     indo
    -0.68
     fallacy
    -0.66
     deduct
    -0.65
     mislead
    -0.65
     offic
    -0.64
     saddened
    -0.64
     dishon
    -0.64
     supporter
    -0.62
    POSITIVE LOGITS
    dylib
    1.07
    jar
    1.03
    0
    1.03
    jpg
    1.02
    gz
    0.97
    zip
    0.93
    840
    0.90
    png
    0.90
    xxx
    0.89
    1
    0.87
    Act Density 0.039%

    No Known Activations