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

    Neuronpedia

    INDEX
    Explanations

    prices or discounts related to technical products

    oai_token-act-pair · gpt-3.5-turbo

    numbers and their significance in a technological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.69
    oyd
    -0.68
    atem
    -0.67
    nih
    -0.65
    anke
    -0.64
    ©¶æ
    -0.62
    etsk
    -0.61
    omial
    -0.57
     forgiven
    -0.57
     mascul
    -0.57
    POSITIVE LOGITS
    th
    1.14
    92
    1.03
    50
    1.03
    55
    1.00
    83
    0.98
    82
    0.97
    40
    0.97
    81
    0.97
    91
    0.96
    87
    0.96
    Act Density 0.107%

    No Known Activations