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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opportunities and suggestions for improvement

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

    following prepositions or verbs

    np_acts-logits-general · gemini-2.0-flash

    words preceding states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kullanılır
    -0.53
    getreten
    -0.52
     sağlar
    -0.50
    жмите
    -0.49
     najdete
    -0.48
    দ্ধ
    -0.48
     raggiunto
    -0.47
    كامل
    -0.47
     sobě
    -0.47
     gangen
    -0.46
    POSITIVE LOGITS
     being
    2.14
     having
    2.06
     getting
    1.91
     making
    1.90
     taking
    1.87
     putting
    1.67
    being
    1.63
     giving
    1.63
     doing
    1.62
     finding
    1.61
    Act Density 2.381%

    No Known Activations