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

    Neuronpedia

    INDEX
    Explanations

    dates in particular months and years

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cot
    -0.72
     ausp
    -0.72
    awaru
    -0.71
    xus
    -0.71
    esc
    -0.70
    rikes
    -0.70
    eeper
    -0.67
    ETF
    -0.66
    terness
    -0.63
     tremend
    -0.63
    POSITIVE LOGITS
    acity
    0.71
    ÙĨ
    0.66
    ulia
    0.64
     Territory
    0.63
    Ability
    0.61
     Rac
    0.60
    ãĥł
    0.58
     Data
    0.57
    ÙĦ
    0.57
     Gram
    0.56
    Act Density 0.069%

    No Known Activations