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

    Neuronpedia

    INDEX
    Explanations

    references to physical space or spatial concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to physical or metaphorical space within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usted
    -0.72
    venge
    -0.68
    ctive
    -0.68
     vengeance
    -0.67
    iamond
    -0.66
    otine
    -0.66
     decap
    -0.65
     Simpson
    -0.63
    ricks
    -0.61
    UCT
    -0.60
    POSITIVE LOGITS
     space
    0.89
     spaces
    0.86
     Layout
    0.85
     occupied
    0.84
    Space
    0.80
     shuttle
    0.79
    bar
    0.79
    alde
    0.78
     constraints
    0.77
    bars
    0.77
    Act Density 0.034%

    No Known Activations