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

    Neuronpedia

    INDEX
    Explanations

    explicit mentions of time periods, especially months

    oai_token-act-pair · gpt-3.5-turbo

    recurring mentions of the term "month" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utf
    -0.71
    UTF
    -0.69
    otle
    -0.68
    ivist
    -0.68
    anooga
    -0.66
    unders
    -0.66
    ioch
    -0.66
    eches
    -0.63
    ocratic
    -0.63
    sav
    -0.63
    POSITIVE LOGITS
    theless
    0.93
    etheless
    0.91
    tom
    0.85
    iversary
    0.82
     ago
    0.82
    ruary
    0.81
    lies
    0.80
    ths
    0.80
    wise
    0.78
    flower
    0.75
    Act Density 0.014%

    No Known Activations