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

    Neuronpedia

    INDEX
    Explanations

    time intervals in a schedule

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly related to time or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rament
    -0.81
    raltar
    -0.75
    azeera
    -0.75
    ilial
    -0.71
    ulet
    -0.71
    idates
    -0.70
    paio
    -0.69
     tremend
    -0.69
    necess
    -0.68
    achus
    -0.67
    POSITIVE LOGITS
    rm
    0.70
     [+]
    0.70
     footnote
    0.68
     WAR
    0.68
     WRITE
    0.67
    3333
    0.64
     [*]
    0.64
     TJ
    0.63
     =================================================================
    0.63
    jp
    0.63
    Act Density 0.088%

    No Known Activations