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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    the mention of a specific term related to a cultural or social concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     almonds
    -0.71
     withholding
    -0.66
    terday
    -0.63
    IVES
    -0.61
    meal
    -0.61
     behold
    -0.61
     Highlander
    -0.61
    ¿½
    -0.60
     preferential
    -0.60
     braces
    -0.60
    POSITIVE LOGITS
    ultane
    1.60
    psons
    1.36
    iliar
    1.36
    ulators
    1.34
    ulations
    1.32
    ply
    1.26
    pler
    1.25
    ulator
    1.22
    pson
    1.21
    ulation
    1.19
    Act Density 0.034%

    No Known Activations