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

    Neuronpedia

    INDEX
    Explanations

    numerical information formatted as dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 29

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allo
    -0.85
    omial
    -0.82
    algia
    -0.81
    ates
    -0.79
    rid
    -0.75
    ãĤ¹ãĥĪ
    -0.73
    ento
    -0.73
    atum
    -0.73
    itious
    -0.72
    oday
    -0.72
    POSITIVE LOGITS
    00
    0.96
    09
    0.83
    06
    0.81
    08
    0.79
    29
    0.79
    VEL
    0.79
    79
    0.78
    th
    0.78
    05
    0.77
    ATH
    0.77
    Act Density 0.015%

    No Known Activations