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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate comparison or contrast

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

    rewards and triumphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.47
    AndEndTag
    -0.47
    TabIndex
    -0.46
    /***/
    -0.44
     незавершена
    -0.43
    Disadvantages
    -0.41
    httphttps
    -0.40
    getDoctrine
    -0.40
     getItemCount
    -0.39
     resourceCulture
    -0.38
    POSITIVE LOGITS
     successes
    0.85
     triumphs
    0.80
     triumph
    0.71
     reward
    0.69
     triumphant
    0.67
     rewards
    0.67
     Triumph
    0.65
    success
    0.64
    reward
    0.64
     triump
    0.63
    Act Density 0.187%

    No Known Activations