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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with reinforcing or supporting actions or concepts

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

    strengthen or reaffirm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.56
    LookAnd
    -0.41
    アダ
    -0.40
    ล้ว
    -0.38
    Complexity
    -0.37
    multer
    -0.37
     couteau
    -0.36
     GenerationType
    -0.35
    くら
    -0.35
     caviar
    -0.35
    POSITIVE LOGITS
     reinforce
    1.34
     reinforces
    1.29
     reinforcing
    1.25
     reforzar
    1.07
     reinforced
    0.98
     refuer
    0.98
     reinforcement
    0.93
     renforcer
    0.91
     renfor
    0.85
     reaffirm
    0.82
    Act Density 0.004%

    No Known Activations