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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations, paths, and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    descriptive locations or directions in a travel or exploration context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.82
    Professional
    -0.78
    professional
    -0.77
     affirmative
    -0.74
     Baldwin
    -0.73
     SNAP
    -0.73
     professionalism
    -0.72
    Hamilton
    -0.69
     ÂŃ
    -0.69
     indign
    -0.69
    POSITIVE LOGITS
     dungeons
    1.53
     caves
    1.52
     Ruins
    1.51
     dungeon
    1.47
     cavern
    1.47
     Cavern
    1.42
     ruins
    1.31
     tunnels
    1.30
     cave
    1.29
     castle
    1.29
    Act Density 0.348%

    No Known Activations