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

    Neuronpedia

    INDEX
    Explanations

    directional instructions for navigating a specific path

    oai_token-act-pair · gpt-3.5-turbo

    directions and navigational guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recipients
    -0.70
    luaj
    -0.64
     jealous
    -0.64
     redund
    -0.64
     recipient
    -0.63
     moderator
    -0.62
     inbox
    -0.62
     moderators
    -0.62
     contractual
    -0.62
     vitro
    -0.62
    POSITIVE LOGITS
     uphill
    1.25
     downhill
    1.07
    atown
    1.02
     Highway
    0.98
     Exit
    0.98
     stairs
    0.97
     Parking
    0.96
    Exit
    0.96
     climb
    0.95
    south
    0.95
    Act Density 0.276%

    No Known Activations