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

    Neuronpedia

    INDEX
    Explanations

    words related to tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to various tasks and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ental
    -0.75
    LECT
    -0.74
    vae
    -0.70
    STD
    -0.66
    pac
    -0.64
    cott
    -0.63
    Sov
    -0.63
     Geo
    -0.62
     Neph
    -0.62
    oil
    -0.62
    POSITIVE LOGITS
     tasks
    1.04
    task
    0.88
     task
    0.86
     sched
    0.83
    asks
    0.81
    manship
    0.77
    station
    0.74
    ¯
    0.74
    icular
    0.73
    ername
    0.72
    Act Density 0.013%

    No Known Activations