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

    Neuronpedia

    INDEX
    Explanations

    mentions of alumni or former students

    oai_token-act-pair · gpt-3.5-turbo

    references to alumni and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakens
    -0.81
    ©¶æ
    -0.70
     Nightmares
    -0.68
    lights
    -0.67
    mare
    -0.65
    geist
    -0.64
    maid
    -0.62
    VERTIS
    -0.62
     Prometheus
    -0.60
     Matter
    -0.59
    POSITIVE LOGITS
    doms
    0.91
    vana
    0.83
    channelAvailability
    0.82
    icably
    0.81
    oing
    0.80
    sin
    0.79
    sung
    0.76
    ensis
    0.73
    yip
    0.72
    oba
    0.69
    Act Density 0.137%

    No Known Activations