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

    Neuronpedia

    INDEX
    Explanations

    references to specific years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with shared experiences or collective knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...)
    -0.61
    âĢ¦)
    -0.60
    !)
    -0.59
    -)
    -0.57
    )"
    -0.54
    âĢ¦]
    -0.53
     })
    -0.52
    Loading
    -0.51
    \-
    -0.51
     physic
    -0.50
    POSITIVE LOGITS
    etheless
    1.04
    iannopoulos
    0.73
     âĵĺ
    0.60
     Pruitt
    0.59
    abbit
    0.56
    AFP
    0.56
     Trotsky
    0.55
     largeDownload
    0.55
    collect
    0.54
     Mulcair
    0.54
    Act Density 2.640%

    No Known Activations