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

    Neuronpedia

    INDEX
    Explanations

    phrases related to works that are in progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing efforts or developments, particularly related to work and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.74
    edu
    -0.65
    dot
    -0.63
    baugh
    -0.62
    pora
    -0.62
    ricular
    -0.61
    áµ
    -0.61
    mort
    -0.61
    ibrary
    -0.59
    myra
    -0.59
    POSITIVE LOGITS
     Progress
    0.90
    Progress
    0.84
     progress
    0.80
    progress
    0.78
     PROG
    0.66
    intensive
    0.65
     stalls
    0.65
     Occupations
    0.63
    pause
    0.62
     progresses
    0.62
    Act Density 0.151%

    No Known Activations