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

    Neuronpedia

    INDEX
    Explanations

    mentions of old or traditional elements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "old" or outdated things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.92
    ï¸ı
    -0.83
    gur
    -0.82
    ommod
    -0.82
     ILCS
    -0.80
    amera
    -0.80
    atography
    -0.78
    illation
    -0.76
    rencies
    -0.73
    OTUS
    -0.71
    POSITIVE LOGITS
     fashioned
    1.48
     timers
    1.02
     standby
    1.01
    est
    0.93
    fashioned
    0.91
    school
    0.87
     school
    0.84
     stomp
    0.84
     Testament
    0.79
     testament
    0.76
    Act Density 0.033%

    No Known Activations