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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploration and travel

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to exploration and global context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recharge
    -0.77
    arb
    -0.75
    paio
    -0.74
    Plex
    -0.72
    ebus
    -0.72
    Harris
    -0.71
     cider
    -0.71
     Perkins
    -0.70
     Canter
    -0.70
    cium
    -0.67
    POSITIVE LOGITS
     World
    2.18
     WORLD
    2.06
    World
    2.03
    world
    1.89
     world
    1.77
     Worlds
    1.66
     Worldwide
    1.55
     globe
    1.51
     Global
    1.49
     global
    1.46
    Act Density 0.184%

    No Known Activations