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

    Neuronpedia

    INDEX
    Explanations

    issues related to social and legal responsibilities, particularly concerning children and decision-making

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

    commas that follow potentially sensitive or negative content words.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    éez
    -0.39
     actionMode
    -0.36
    uresti
    -0.35
     GenerationType
    -0.35
     glab
    -0.34
     mencer
    -0.34
     Pere
    -0.32
    ogno
    -0.32
    :][
    -0.32
     utilisons
    -0.32
    POSITIVE LOGITS
     solange
    1.50
    只要
    1.49
     Provided
    1.31
     provided
    1.30
    Provided
    1.26
    provided
    1.25
     PROVIDED
    1.07
     miễn
    1.05
     بشر
    0.98
     föruts
    0.96
    Act Density 0.699%

    No Known Activations