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

    Neuronpedia

    INDEX
    Explanations

    references to military or security-related checkpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to checkpoints and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geist
    -0.69
    Ear
    -0.69
     Sor
    -0.67
     mould
    -0.67
    casting
    -0.66
     Cats
    -0.65
    cast
    -0.65
     Gott
    -0.64
    elong
    -0.64
    rice
    -0.62
    POSITIVE LOGITS
     checkpoint
    3.93
     checkpoints
    3.66
     bottleneck
    1.32
     blockade
    1.17
     outpost
    1.14
     patrols
    1.10
     barric
    1.06
     curfew
    1.05
     respawn
    1.03
     TSA
    1.02
    Act Density 0.015%

    No Known Activations