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

    Neuronpedia

    INDEX
    Explanations

    words related to proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "smol" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Refuge
    -0.68
     Exit
    -0.64
     Cortex
    -0.63
     Triangle
    -0.63
     reservation
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     unfocusedRange
    -0.60
     dime
    -0.59
     tert
    -0.59
     Camer
    -0.59
    POSITIVE LOGITS
    glers
    0.94
    rill
    0.87
    wear
    0.83
    vity
    0.81
    iland
    0.81
    chery
    0.79
    etsk
    0.78
    lein
    0.75
    cer
    0.74
    ety
    0.74
    Act Density 0.070%

    No Known Activations