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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay" or its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cref
    -0.56
    userDao
    -0.53
    zzleHttp
    -0.52
    存于互联网档案馆
    -0.52
     AttributeError
    -0.50
    NameInMap
    -0.50
    minecraftforge
    -0.49
     Chwiliwch
    -0.49
    InjectMocks
    -0.48
     SRS
    -0.47
    POSITIVE LOGITS
    Stay
    1.01
     Stay
    1.01
     stay
    0.94
    stay
    0.90
     STAY
    0.84
     stayed
    0.81
    STAY
    0.79
    Remain
    0.77
     Remain
    0.76
     staying
    0.74
    Act Density 0.079%

    No Known Activations