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

    Neuronpedia

    INDEX
    Explanations

    words related to connections or associations between different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to connections or relationships between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.74
     Penguins
    -0.66
     Nights
    -0.65
    sburg
    -0.64
    oplan
    -0.64
     Sabres
    -0.61
    ODUCT
    -0.60
    ZI
    -0.60
    ccording
    -0.60
    thur
    -0.60
    POSITIVE LOGITS
     link
    0.98
    link
    0.97
    chain
    0.93
     links
    0.93
     linking
    0.91
    edin
    0.91
    later
    0.89
     connecting
    0.87
    linked
    0.84
    links
    0.84
    Act Density 0.032%

    No Known Activations