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

    Neuronpedia

    INDEX
    Explanations

    words related to shapes and forms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geometric or structural forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onte
    -0.78
    uthor
    -0.75
    idden
    -0.73
    iddy
    -0.71
    ittle
    -0.71
    ICE
    -0.71
    wolves
    -0.70
    uld
    -0.65
    yr
    -0.65
    essional
    -0.64
    POSITIVE LOGITS
     resemblance
    1.03
     resembles
    0.93
     dimensions
    0.85
     consistency
    0.85
     similarity
    0.84
     shape
    0.84
     texture
    0.82
     resembled
    0.82
     alteration
    0.82
     profile
    0.82
    Act Density 0.179%

    No Known Activations