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

    Neuronpedia

    INDEX
    Explanations

    phrases related to function return statements and their expected outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.75
    kuuta
    -0.64
    كويكب
    -0.58
     seyn
    -0.57
     neceff
    -0.57
    indeed
    -0.57
     devoir
    -0.56
    mybatisplus
    -0.55
     kura
    -0.55
    addLast
    -0.55
    POSITIVE LOGITS
     returns
    1.10
    return
    1.10
     Return
    1.07
     RETURN
    1.03
     return
    1.03
     Returns
    1.00
    returns
    0.98
    返回
    0.96
     返回
    0.95
     returned
    0.94
    Act Density 0.107%

    No Known Activations