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

    Neuronpedia

    INDEX
    Explanations

    references to time in the near future

    oai_token-act-pair · gpt-3.5-turbo

    references to upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocker
    -0.68
     Feldman
    -0.68
    lee
    -0.67
     Legions
    -0.65
     Sinai
    -0.64
    enance
    -0.63
    lees
    -0.62
    ini
    -0.62
    iveness
    -0.61
    kson
    -0.60
    POSITIVE LOGITS
    ĻĤ
    0.84
     week
    0.84
     millenn
    0.82
    NetMessage
    0.77
     generations
    0.75
     generation
    0.75
     neighb
    0.75
     door
    0.74
     compr
    0.73
     month
    0.72
    Act Density 0.034%

    No Known Activations