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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing encryption key sizes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to computer specifications and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ago
    -0.70
     Ox
    -0.68
     Chavez
    -0.67
     Huss
    -0.66
    chu
    -0.66
     Wag
    -0.64
     Osh
    -0.64
     Marty
    -0.63
     Pav
    -0.63
    ogie
    -0.62
    POSITIVE LOGITS
     256
    2.75
    256
    2.68
     512
    2.34
    512
    2.17
     128
    2.13
     1024
    1.97
    128
    1.79
    255
    1.78
    1024
    1.76
     4096
    1.70
    Act Density 0.042%

    No Known Activations