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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to planning and organization

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to awareness and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.81
    ructose
    -0.73
    ©¶æ¥µ
    -0.73
    rica
    -0.69
    ellen
    -0.67
    phia
    -0.66
    cius
    -0.66
    ugen
    -0.66
    ĸļ
    -0.65
    cember
    -0.64
    POSITIVE LOGITS
     decisions
    1.07
     tasks
    1.07
     them
    1.05
     objects
    1.01
     things
    1.01
     nuances
    1.01
     whatever
    0.98
     situations
    0.97
     motions
    0.97
     each
    0.97
    Act Density 0.454%

    No Known Activations