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

    Neuronpedia

    INDEX
    Explanations

    words related to structure and organization

    oai_token-act-pair · gpt-3.5-turbo

    words related to structure and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kins
    -0.79
     Yel
    -0.72
     Sonny
    -0.64
     Clarkson
    -0.63
    kin
    -0.61
    agascar
    -0.61
    cli
    -0.61
     Bryant
    -0.59
     Fallon
    -0.58
     Enrique
    -0.58
    POSITIVE LOGITS
    urally
    1.46
    ured
    1.27
    ural
    1.25
    uring
    1.17
    ures
    1.12
    urers
    0.99
    urer
    0.97
    ivist
    0.95
    uration
    0.94
    ible
    0.90
    Act Density 0.046%

    No Known Activations