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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial concepts, specifically indicating a location or direction

    oai_token-act-pair · gpt-3.5-turbo

    references to "the other side" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GM
    -0.67
    Deal
    -0.66
     Entered
    -0.65
    ACP
    -0.61
     Inher
    -0.60
    Coach
    -0.59
     Playoff
    -0.57
     Serve
    -0.57
    essed
    -0.56
    Grab
    -0.56
    POSITIVE LOGITS
    worldly
    0.78
    than
    0.73
     altogether
    0.69
    ottest
    0.66
    arie
    0.65
     than
    0.64
    blance
    0.62
    bang
    0.61
    arettes
    0.60
    axis
    0.60
    Act Density 0.107%

    No Known Activations