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

    Neuronpedia

    INDEX
    Explanations

    words related to randomness or random selection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "randomly" and "accidentally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.78
    antics
    -0.75
    ger
    -0.72
    ador
    -0.70
    rers
    -0.69
     attainment
    -0.68
    soc
    -0.68
    uese
    -0.68
    ryu
    -0.67
    ges
    -0.67
    POSITIVE LOGITS
     detonated
    0.84
     stumbled
    0.80
     worshipped
    0.78
     bumped
    0.76
     located
    0.75
     combust
    0.75
     planted
    0.75
     placed
    0.74
     timed
    0.74
     chose
    0.73
    Act Density 0.034%

    No Known Activations