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

    Neuronpedia

    INDEX
    Explanations

    keywords related to planning, organization, and coordination of tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predecessor
    -0.67
    enegger
    -0.60
     successor
    -0.60
     acronym
    -0.57
    washer
    -0.54
     pupil
    -0.51
    theless
    -0.51
     interviewer
    -0.50
     entrepreneur
    -0.50
    ãĤ´ãĥ³
    -0.50
    POSITIVE LOGITS
     alike
    0.71
     theirs
    0.70
     themselves
    0.68
     riot
    0.67
    selves
    0.63
    their
    0.60
     converge
    0.58
    ble
    0.57
    represented
    0.56
     THEIR
    0.55
    Act Density 0.707%

    No Known Activations