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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to thickness or density

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thick" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FAULT
    -0.79
    OTA
    -0.79
    Particip
    -0.75
    DB
    -0.70
    shows
    -0.70
     Controlled
    -0.70
     Judicial
    -0.70
    OUT
    -0.69
    OPA
    -0.69
    USA
    -0.68
    POSITIVE LOGITS
    ening
    1.23
    ened
    1.17
     thick
    1.13
     thickness
    1.10
     thicker
    1.07
    layer
    0.94
     nodd
    0.94
    ciating
    0.94
    nesses
    0.92
     tremend
    0.91
    Act Density 0.006%

    No Known Activations