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

    Neuronpedia

    INDEX
    Explanations

    words related to intensity or high energy level

    oai_token-act-pair · gpt-3.5-turbo

    terms related to luxury and excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alone
    -0.61
     Clover
    -0.61
     HC
    -0.60
     Command
    -0.59
     context
    -0.59
     rookies
    -0.59
     command
    -0.58
    WR
    -0.58
     dove
    -0.56
     CBS
    -0.56
    POSITIVE LOGITS
    ulent
    4.74
    ulence
    3.59
    oreal
    1.22
    ulous
    1.20
    ilion
    1.19
    yip
    1.14
    aceous
    1.10
    idious
    1.09
    ulus
    1.08
    urous
    1.08
    Act Density 0.030%

    No Known Activations