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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dinner
    -0.73
     Kern
    -0.68
     Cotton
    -0.67
     Cum
    -0.66
    HCR
    -0.65
     Cec
    -0.64
    pload
    -0.64
    ModLoader
    -0.64
     congratulated
    -0.64
    ulhu
    -0.64
    POSITIVE LOGITS
    based
    1.31
    related
    1.24
    driven
    1.22
    oriented
    1.21
    seeking
    1.20
    sensitive
    1.18
    intensive
    1.18
    management
    1.14
    wise
    1.14
    controlled
    1.09
    Act Density 0.103%

    No Known Activations