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

    Neuronpedia

    INDEX
    Explanations

    different layers of objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to "layers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Predators
    -0.81
    swick
    -0.76
     Spe
    -0.74
    eve
    -0.72
    ãĥīãĥ©
    -0.71
    cgi
    -0.70
     Wand
    -0.69
    sburgh
    -0.69
    date
    -0.68
    shire
    -0.67
    POSITIVE LOGITS
     layers
    1.74
    layer
    1.29
     layer
    1.21
     layered
    1.16
    ayers
    1.07
    avorite
    1.06
     misunder
    0.94
     Layer
    0.93
    Layer
    0.92
     opacity
    0.90
    Act Density 0.005%

    No Known Activations