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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causal relationships or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    as a result of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.62
     purpoſe
    -0.61
     itſelf
    -0.53
     ſtand
    -0.53
     houſe
    -0.52
     myſelf
    -0.52
     ſche
    -0.51
     faſt
    -0.48
     Chriftian
    -0.48
     beſt
    -0.48
    POSITIVE LOGITS
     результате
    0.67
     urma
    0.63
     akibat
    0.63
     infolge
    0.63
    rzez
    0.60
     نتيجة
    0.60
     resourceCulture
    0.58
     seguito
    0.56
     karena
    0.56
    ibatkan
    0.55
    Act Density 0.026%

    No Known Activations