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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical actions and movements, particularly those involving walking, running, jumping, and physical interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to group activities and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Understanding
    -0.81
    felt
    -0.77
     Continued
    -0.76
     Improvement
    -0.75
     Regarding
    -0.74
    states
    -0.74
    classified
    -0.73
    answered
    -0.73
     Horizon
    -0.73
    significant
    -0.72
    POSITIVE LOGITS
     snatch
    1.30
     lure
    1.27
     plunder
    1.26
     roam
    1.26
     gob
    1.23
     taunt
    1.23
     indulge
    1.23
     ambush
    1.23
     bribe
    1.22
     swoop
    1.21
    Act Density 0.441%

    No Known Activations