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

    Neuronpedia

    INDEX
    Explanations

    text segments that are separated by a special character sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of game-related information or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifes
    -0.73
    ÃŃs
    -0.72
     intervened
    -0.71
     laughter
    -0.68
     herself
    -0.66
     Commonwealth
    -0.65
     interven
    -0.65
     traveling
    -0.64
     deport
    -0.64
     lived
    -0.64
    POSITIVE LOGITS
    Samsung
    1.08
    Liquid
    1.06
    Hardware
    1.04
    ccording
    1.02
    Speaking
    1.00
    DON
    1.00
    âķIJâķIJ
    0.98
    Intel
    0.98
    Android
    0.97
    Meanwhile
    0.97
    Act Density 0.593%

    No Known Activations