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

    Neuronpedia

    INDEX
    Explanations

    dates and timestamps in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of posted dates or timestamps in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.76
    ãĥ¯ãĥ³
    -0.72
    ifted
    -0.70
    oller
    -0.69
    vernment
    -0.68
    stood
    -0.67
    fitting
    -0.65
    ively
    -0.63
    aster
    -0.62
    phas
    -0.60
    POSITIVE LOGITS
     Apr
    0.82
    escription
    0.77
     by
    0.74
     Tue
    0.73
     Thu
    0.72
    itors
    0.70
     05
    0.70
     Feb
    0.69
     Comments
    0.69
     By
    0.69
    Act Density 0.021%

    No Known Activations