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

    Neuronpedia

    INDEX
    Explanations

    web-related terms, such as 'Website', 'web', 'international', 'Haskell', and 'table'

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-existent textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cheong
    -0.69
    lves
    -0.68
    ioned
    -0.66
    ilogy
    -0.66
    wagen
    -0.65
     Doomsday
    -0.65
    vez
    -0.65
    jad
    -0.63
    leon
    -0.62
    quez
    -0.60
    POSITIVE LOGITS
     purposes
    1.70
     sake
    1.60
    ummies
    1.08
     reasons
    1.05
     purpose
    0.80
     emergencies
    0.77
     beginners
    0.74
     foreseeable
    0.69
     lovers
    0.69
    gress
    0.69
    Act Density 0.489%

    No Known Activations