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

    Neuronpedia

    INDEX
    Explanations

    phrases related to depth or deep locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of depth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orious
    -0.86
    cules
    -0.72
     Machina
    -0.67
    ICAN
    -0.66
    ery
    -0.66
    icans
    -0.66
     AUTHOR
    -0.65
     ATT
    -0.65
    jee
    -0.65
     Prosecut
    -0.65
    POSITIVE LOGITS
     vein
    1.03
    ened
    0.92
     seeded
    0.89
     deep
    0.88
     depth
    0.88
     penetration
    0.87
     depths
    0.86
     penetrating
    0.81
     trenches
    0.80
     throat
    0.79
    Act Density 0.019%

    No Known Activations