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

    Neuronpedia

    INDEX
    Explanations

    references to external entities or factors

    oai_token-act-pair · gpt-3.5-turbo

    references to external and internal entities or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    birds
    -0.79
    EY
    -0.79
    ander
    -0.76
    ony
    -0.75
    oned
    -0.75
    killer
    -0.73
    SHIP
    -0.73
    geist
    -0.73
    rano
    -0.72
    hess
    -0.72
    POSITIVE LOGITS
    ities
    1.14
    ized
    1.00
    izing
    0.90
    ization
    0.85
     combustion
    0.84
     affairs
    0.84
    izable
    0.84
    izations
    0.83
    izers
    0.81
    izes
    0.81
    Act Density 0.022%

    No Known Activations