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

    Neuronpedia

    INDEX
    Explanations

    time-related information such as specific weeks, months, or seasons

    oai_token-act-pair · gpt-3.5-turbo

    temporal references related to weeks and seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toc
    -0.68
    mson
    -0.60
    opol
    -0.60
    ibrary
    -0.59
    abase
    -0.59
    CRE
    -0.58
     manure
    -0.58
     boat
    -0.57
     phyl
    -0.57
     plank
    -0.56
    POSITIVE LOGITS
    nis
    0.74
    lier
    0.72
    grade
    0.71
    terms
    0.68
    oa
    0.67
    è£ħ
    0.66
    itor
    0.65
    ãĥ¼ãĥĨãĤ£
    0.64
    oi
    0.63
    ãĥĥãĥī
    0.62
    Act Density 0.507%

    No Known Activations