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

    Neuronpedia

    INDEX
    Explanations

    reported speech or attribution in discussions

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

    attribution of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.49
    ChildScrollView
    -0.47
     Offisielt
    -0.46
    原始内容存档于
    -0.45
     internetowa
    -0.44
     propOrder
    -0.43
     szczegó
    -0.41
    bcryptjs
    -0.40
     dieux
    -0.40
     aprendido
    -0.39
    POSITIVE LOGITS
    évaluateur
    0.51
     Tong
    0.44
    comment
    0.43
     Zionist
    0.43
    cinct
    0.42
    phil
    0.41
    arton
    0.41
    HORE
    0.41
     Jain
    0.41
    blob
    0.41
    Act Density 0.020%

    No Known Activations