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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods and ages

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and memories associated with reading and age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -1.39
    âĢij
    -1.03
    —
    -1.02
    ÂŃ
    -0.98
    —"
    -0.97
     âĢķ
    -0.95
    "—
    -0.93
    Åį
    -0.88
     —
    -0.86
    Enlarge
    -0.85
    POSITIVE LOGITS
     alot
    1.63
     doesnt
    1.47
     didnt
    1.47
     dont
    1.37
     thru
    1.36
     HUGE
    1.26
     VERY
    1.22
     ONLY
    1.18
     tho
    1.15
     EVERY
    1.15
    Act Density 1.842%

    No Known Activations