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

    Neuronpedia

    INDEX
    Explanations

    moments or actions of looking at specific locations or people in various situations

    oai_token-act-pair · gpt-3.5-turbo

    actions of looking or observing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isma
    -0.68
    BER
    -0.67
    TOP
    -0.65
    ero
    -0.59
    ETF
    -0.59
    BLIC
    -0.59
     Burning
    -0.58
    EStreamFrame
    -0.57
    uala
    -0.56
    MAT
    -0.56
    POSITIVE LOGITS
     afar
    0.78
     favorably
    0.72
     helpless
    0.71
    lights
    0.70
     Compass
    0.70
    screen
    0.70
     lenses
    0.69
    scope
    0.68
     symp
    0.67
     Miko
    0.67
    Act Density 0.143%

    No Known Activations