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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial and temporal information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spatial and temporal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nuts
    -0.80
    warts
    -0.77
    orship
    -0.73
    nut
    -0.73
    EGA
    -0.73
    doms
    -0.73
    rug
    -0.71
    sen
    -0.71
    kins
    -0.70
    cart
    -0.69
    POSITIVE LOGITS
     lobe
    0.99
    ities
    0.97
     spatial
    0.95
     temporal
    0.91
     distortions
    0.84
     accuracy
    0.78
     dimension
    0.78
     aber
    0.78
     vibrations
    0.76
     dimensions
    0.76
    Act Density 0.024%

    No Known Activations