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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating appreciation or recognition of actions or qualities

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

    Positive sentiment towards good service or treatment

    np_acts-logits-general · gemini-2.0-flash

    receiving attention or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.62
    ArgsConstructor
    -0.58
    afterEach
    -0.57
     geme
    -0.55
    Bibliografía
    -0.55
    Initializable
    -0.54
     reproducibility
    -0.52
    PDOException
    -0.52
    fficacy
    -0.52
    inta
    -0.51
    POSITIVE LOGITS
     treatment
    1.43
     attention
    1.42
    treatment
    1.27
    attention
    1.26
     Treatment
    1.17
     Attention
    1.14
    Treatment
    1.14
     treated
    1.09
    Attention
    1.08
     atenção
    1.08
    Act Density 0.242%

    No Known Activations