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

    Neuronpedia

    INDEX
    Explanations

    locations or directions, specifically focusing on the west side

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic directions, specifically 'west' and 'east'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anamo
    -0.82
     Parenthood
    -0.81
    Maker
    -0.78
     Meter
    -0.75
    thood
    -0.75
    Testing
    -0.72
    vous
    -0.72
    Poll
    -0.72
     Likes
    -0.72
    abulary
    -0.71
    POSITIVE LOGITS
    ward
    1.18
     coast
    1.05
    side
    1.01
    wards
    0.96
     hemisphere
    0.87
    bound
    0.87
     wing
    0.84
     flank
    0.81
     side
    0.80
     coasts
    0.80
    Act Density 0.022%

    No Known Activations