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

    Neuronpedia

    INDEX
    Explanations

    references to different layers, both literal and metaphorical

    oai_token-act-pair · gpt-3.5-turbo

    references to different layers in systems or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.80
     Predators
    -0.77
     STAR
    -0.73
    date
    -0.71
    etheus
    -0.70
    nia
    -0.70
    WAR
    -0.69
    speaking
    -0.67
    lishing
    -0.67
     FRE
    -0.66
    POSITIVE LOGITS
     layers
    1.44
     layer
    1.30
    layer
    1.00
     Layer
    0.98
    Layer
    0.96
     thickness
    0.92
     coats
    0.87
    coat
    0.82
     opacity
    0.81
     layered
    0.79
    Act Density 0.018%

    No Known Activations