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

    Neuronpedia

    INDEX
    Explanations

    measurements and characteristics of objects

    oai_token-act-pair · gpt-3.5-turbo

    descriptive attributes and measurements related to physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.75
    aughs
    -0.71
    iseum
    -0.70
    odcast
    -0.68
    ontent
    -0.68
    Politics
    -0.67
    imore
    -0.67
    hovah
    -0.66
    funding
    -0.65
    Events
    -0.64
    POSITIVE LOGITS
     protr
    1.19
     translucent
    1.06
     elong
    1.02
     diameter
    0.98
     cyl
    0.97
     triangular
    0.91
     rectangular
    0.90
     curved
    0.90
     thickness
    0.89
     curv
    0.88
    Act Density 1.146%

    No Known Activations