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

    Neuronpedia

    INDEX
    Explanations

    terms related to three-dimensional representations or illusions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dimensionality in spatial representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INST
    -0.73
    ICA
    -0.70
    AV
    -0.69
    ALT
    -0.67
    UES
    -0.65
    raltar
    -0.64
    MU
    -0.64
    exec
    -0.64
    creen
    -0.62
    CHAT
    -0.61
    POSITIVE LOGITS
    imensional
    1.33
    dimensional
    1.15
     dimensional
    1.00
    ikuman
    0.92
    ĸļ
    0.91
    dimension
    0.85
     ILCS
    0.77
    ynamic
    0.76
    hyde
    0.76
     dimension
    0.75
    Act Density 0.010%

    No Known Activations