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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related expressions, particularly months

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     textual
    -0.74
     veins
    -0.63
    Notice
    -0.61
    >[
    -0.60
    Status
    -0.59
     fixation
    -0.59
    abilia
    -0.59
     scope
    -0.58
    esse
    -0.58
    Entry
    -0.58
    POSITIVE LOGITS
    obyl
    0.75
    when
    0.73
    女
    0.72
     when
    0.68
     Giul
    0.68
    uca
    0.66
    etsk
    0.65
    lished
    0.64
     Harbor
    0.63
     belonged
    0.62
    Act Density 0.099%

    No Known Activations