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

    Neuronpedia

    INDEX
    Explanations

    encryption-related terms or references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Enc" and related terms or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otent
    -0.74
    mitt
    -0.72
     tube
    -0.70
    figured
    -0.69
     pans
    -0.68
     sou
    -0.68
     tou
    -0.66
    uted
    -0.66
    tom
    -0.65
     rocket
    -0.64
    POSITIVE LOGITS
     Enc
    3.66
    Enc
    2.27
     Encounter
    1.37
     Esc
    1.07
    enc
    1.01
    Esc
    1.00
     Celebration
    0.96
     Decoder
    0.95
     Battles
    0.92
     Codec
    0.91
    Act Density 0.009%

    No Known Activations