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

    Neuronpedia

    INDEX
    Explanations

    comparative questions and discussions about preferences

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

    greater or bigger comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    devamını
    -0.47
     Conſ
    -0.44
    Enllaces
    -0.43
    migrationBuilder
    -0.41
     Diſ
    -0.40
    Ligações
    -0.40
    queryInterface
    -0.40
     perſon
    -0.38
     pleaſure
    -0.38
     Reſ
    -0.37
    POSITIVE LOGITS
    تقاوى
    0.55
    mutual
    0.48
    TargetException
    0.46
    SequentialGroup
    0.45
     mutual
    0.45
    Mutual
    0.45
    誰が
    0.44
    どっち
    0.44
    MessageOf
    0.44
    रीद
    0.42
    Act Density 0.243%

    No Known Activations