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

    Neuronpedia

    INDEX
    Explanations

    references to personal writings or journals

    oai_token-act-pair · gpt-3.5-turbo

    references to diaries or personal accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Universities
    -0.73
     scholarships
    -0.69
     srf
    -0.69
    FFFF
    -0.68
    represented
    -0.66
     evenly
    -0.66
     Hispanic
    -0.65
     mutual
    -0.65
    sci
    -0.64
    olulu
    -0.63
    POSITIVE LOGITS
     diary
    1.20
     Diary
    1.10
    wallet
    0.72
    urnal
    0.70
     Timeline
    0.69
    ogue
    0.69
    cam
    0.69
    ãĥĥãĤ¯
    0.66
    sonian
    0.66
     entries
    0.66
    Act Density 0.014%

    No Known Activations